Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

VectorDB support (pgvector) for archival memory (#226)

Browse Source
This commit is contained in:
Sarah Wooders
2023-11-03 16:19:15 -07:00
committed by GitHub
parent c1fd8d6df1
commit b9ce763fda
25 changed files with 1480 additions and 384 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
.github/workflows/sarah-test.yml vendored Normal file
View File

@@ -0,0 +1,40 @@
name: sarah-test
on:
release:
types: [published]
workflow_dispatch:
env:
EXAMPLE_VAR: "hello_world"
PGVECTOR_TEST_DB_URL: ${{ secrets.PGVECTOR_TEST_DB_URL }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
jobs:
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.10.10 # Set this to your Python version
- name: Install Poetry
run: |
pip install poetry
- name: Install dependencies using Poetry
run: |
poetry install
- name: Install pexpect for testing the interactive CLI
run: |
poetry add --dev pexpect
- name: Run tests with pytest
env:
EXAMPLE_VAR: "hello_world"
PGVECTOR_TEST_DB_URL: ${{ secrets.PGVECTOR_TEST_DB_URL }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
run: |
PGVECTOR_TEST_DB_URL=${{ secrets.PGVECTOR_TEST_DB_URL }} OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }} poetry run pytest -s -vv tests

39
.github/workflows/tests.yml vendored
View File

@@ -1,5 +1,9 @@
name: MemGPT tests
env:
PGVECTOR_TEST_DB_URL: ${{ secrets.PGVECTOR_TEST_DB_URL }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
on:
push:
branches: [ main ]
@@ -11,26 +15,45 @@ jobs:
runs-on: ubuntu-latest
env:
PGVECTOR_TEST_DB_URL: ${{ secrets.PGVECTOR_TEST_DB_URL }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v1
- name: Install poetry
run: pipx install poetry
- name: Set up Python
uses: actions/setup-python@v2
uses: actions/setup-python@v4
with:
python-version: 3.10.10 # Set this to your Python version
python-version: "3.10"
cache: "poetry"
- name: Install Poetry
- name: Set Poetry config
run: |
pip install poetry
poetry config virtualenvs.in-project false
poetry config virtualenvs.path ~/.virtualenvs
- name: Install dependencies using Poetry
env:
PGVECTOR_TEST_DB_URL: ${{ secrets.PGVECTOR_TEST_DB_URL }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
run: |
poetry install
- name: Install pexpect for testing the interactive CLI
- name: Set Poetry config
env:
PGVECTOR_TEST_DB_URL: ${{ secrets.PGVECTOR_TEST_DB_URL }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
run: |
poetry add --dev pexpect
poetry config virtualenvs.in-project false
poetry config virtualenvs.path ~/.virtualenvs
- name: Run tests with pytest
env:
PGVECTOR_TEST_DB_URL: ${{ secrets.PGVECTOR_TEST_DB_URL }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
run: |
poetry run pytest -s -vv tests
PGVECTOR_TEST_DB_URL=${{ secrets.PGVECTOR_TEST_DB_URL }} OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }} poetry run pytest -s -vv tests

7
README.md
View File

@@ -80,7 +80,6 @@ The `run` command supports the following optional flags (if set, will override c
* `--persona`: (str) Name of agent persona to use.
* `--model`: (str) LLM model to run [gpt-4, gpt-3.5].
* `--preset`: (str) MemGPT preset to run agent with.
* `--data-source`: (str) Name of data source (loaded with `memgpt load`) to connect to agent.
* `--first`: (str) Allow user to sent the first message.
* `--debug`: (bool) Show debug logs (default=False)
* `--no-verify`: (bool) Bypass message verification (default=False)
@@ -88,6 +87,7 @@ The `run` command supports the following optional flags (if set, will override c
You can run the following commands in the MemGPT CLI prompt:
* `/exit`: Exit the CLI
* `/attach`: Attach a loaded data source to the agent
* `/save`: Save a checkpoint of the current agent/conversation state
* `/dump`: View the current message log (see the contents of main context)
* `/memory`: Print the current contents of agent memory
@@ -114,7 +114,10 @@ memgpt list [human/persona]
```
### Data Sources (i.e. chat with your data)
MemGPT supports pre-loading data into archival memory, so your agent can reference loaded data in your conversations with an agent by specifying the data source with the flag `memgpt run --data-source <NAME>`.
MemGPT supports pre-loading data into archival memory. You can attach data to your agent (which will place the data in your agent's archival memory) in two ways:
1. Run `memgpt attach --agent <AGENT-NAME> --data-source <DATA-SOURCE-NAME>
2. While chatting with the agent, enter the `/attach` command and select the data source.
#### Loading Data
We currently support loading from a directory and database dumps. We highly encourage contributions for new data sources, which can be added as a new [CLI data load command](https://github.com/cpacker/MemGPT/blob/main/memgpt/cli/cli_load.py).

1
memgpt/agent.py
View File

@@ -381,6 +381,7 @@ class Agent(object):
# load persistence manager
filename = os.path.basename(filename).replace(".json", ".persistence.pickle")
directory = agent_config.save_persistence_manager_dir()
printd(f"Loading persistence manager from {os.path.join(directory, filename)}")
persistence_manager = LocalStateManager.load(os.path.join(directory, filename), agent_config)
messages = state["messages"]

38
memgpt/cli/cli.py
View File

@@ -38,7 +38,6 @@ def run(
human: str = typer.Option(None, help="Specify human"),
model: str = typer.Option(None, help="Specify the LLM model"),
preset: str = typer.Option(None, help="Specify preset"),
data_source: str = typer.Option(None, help="Specify data source to attach to agent"),
first: bool = typer.Option(False, "--first", help="Use --first to send the first message in the sequence"),
strip_ui: bool = typer.Option(False, "--strip_ui", help="Remove all the bells and whistles in CLI output (helpful for testing)"),
debug: bool = typer.Option(False, "--debug", help="Use --debug to enable debugging output"),
@@ -53,7 +52,6 @@ def run(
:param agent: Specify agent name (will load existing state if the agent exists, or create a new one with that name)
:param human: Specify human
:param model: Specify the LLM model
:param data_source: Specify data source to attach to agent (if new agent is being created)
"""
@@ -94,7 +92,7 @@ def run(
config = MemGPTConfig.load()
original_stdout = sys.stdout # unfortunate hack required to suppress confusing print statements from llama index
sys.stdout = io.StringIO()
embed_model = embedding_model(config)
embed_model = embedding_model()
service_context = ServiceContext.from_defaults(llm=None, embed_model=embed_model, chunk_size=config.embedding_chunk_size)
set_global_service_context(service_context)
sys.stdout = original_stdout
@@ -128,8 +126,8 @@ def run(
preset=preset if preset else config.preset,
)
# attach data source to agent
agent_config.attach_data_source(data_source)
## attach data source to agent
# agent_config.attach_data_source(data_source)
# TODO: allow configrable state manager (only local is supported right now)
persistence_manager = LocalStateManager(agent_config) # TODO: insert dataset/pre-fill
@@ -158,4 +156,32 @@ def run(
configure_azure_support()
loop = asyncio.get_event_loop()
loop.run_until_complete(run_agent_loop(memgpt_agent, first, no_verify, config, strip_ui)) # TODO: add back no_verify
loop.run_until_complete(run_agent_loop(memgpt_agent, first, no_verify, config)) # TODO: add back no_verify
def attach(
agent: str = typer.Option(help="Specify agent to attach data to"),
data_source: str = typer.Option(help="Data source to attach to avent"),
):
# loads the data contained in data source into the agent's memory
from memgpt.connectors.storage import StorageConnector
agent_config = AgentConfig.load(agent)
config = MemGPTConfig.load()
# get storage connectors
source_storage = StorageConnector.get_storage_connector(name=data_source)
dest_storage = StorageConnector.get_storage_connector(agent_config=agent_config)
passages = source_storage.get_all()
for p in passages:
len(p.embedding) == config.embedding_dim, f"Mismatched embedding sizes {len(p.embedding)} != {config.embedding_dim}"
dest_storage.insert_many(passages)
dest_storage.save()
total_agent_passages = len(dest_storage.get_all())
typer.secho(
f"Attached data source {data_source} to agent {agent}, consisting of {len(passages)}. Agent now has {total_agent_passages} embeddings in archival memory.",
fg=typer.colors.GREEN,
)

38
memgpt/cli/cli_config.py
View File

@@ -4,6 +4,7 @@ from prettytable import PrettyTable
import typer
import os
import shutil
from collections import defaultdict
# from memgpt.cli import app
from memgpt import utils
@@ -12,6 +13,7 @@ import memgpt.humans.humans as humans
import memgpt.personas.personas as personas
from memgpt.config import MemGPTConfig, AgentConfig
from memgpt.constants import MEMGPT_DIR
from memgpt.connectors.storage import StorageConnector
app = typer.Typer()
@@ -33,7 +35,7 @@ def configure():
openai_key = questionary.text("Open AI API keys not found in enviornment - please enter:").ask()
# azure credentials
use_azure = questionary.confirm("Do you want to enable MemGPT with Azure?").ask()
use_azure = questionary.confirm("Do you want to enable MemGPT with Azure?", default=False).ask()
use_azure_deployment_ids = False
if use_azure:
# search for key in enviornment
@@ -110,6 +112,15 @@ def configure():
# else:
# default_agent = None
# Configure archival storage backend
archival_storage_options = ["local", "postgres"]
archival_storage_type = questionary.select("Select storage backend for archival data:", archival_storage_options, default="local").ask()
archival_storage_uri = None
if archival_storage_type == "postgres":
archival_storage_uri = questionary.text(
"Enter postgres connection string (e.g. postgresql+pg8000://{user}:{password}@{ip}:5432/{database}):"
).ask()
# TODO: allow configuring embedding model
config = MemGPTConfig(
@@ -125,6 +136,8 @@ def configure():
azure_version=azure_version if use_azure else None,
azure_deployment=azure_deployment if use_azure_deployment_ids else None,
azure_embedding_deployment=azure_embedding_deployment if use_azure_deployment_ids else None,
archival_storage_type=archival_storage_type,
archival_storage_uri=archival_storage_uri,
)
print(f"Saving config to {config.config_path}")
config.save()
@@ -139,7 +152,7 @@ def list(option: str):
for agent_file in utils.list_agent_config_files():
agent_name = os.path.basename(agent_file).replace(".json", "")
agent_config = AgentConfig.load(agent_name)
table.add_row([agent_name, agent_config.model, agent_config.persona, agent_config.human, agent_config.data_source])
table.add_row([agent_name, agent_config.model, agent_config.persona, agent_config.human, ",".join(agent_config.data_sources)])
print(table)
elif option == "humans":
"""List all humans"""
@@ -163,10 +176,23 @@ def list(option: str):
elif option == "sources":
"""List all data sources"""
table = PrettyTable()
table.field_names = ["Name", "Create Time", "Agents"]
for data_source_file in os.listdir(os.path.join(MEMGPT_DIR, "archival")):
name = os.path.basename(data_source_file)
table.add_row([name, "TODO", "TODO"])
table.field_names = ["Name", "Location", "Agents"]
config = MemGPTConfig.load()
# TODO: eventually look accross all storage connections
# TODO: add data source stats
source_to_agents = {}
for agent_file in utils.list_agent_config_files():
agent_name = os.path.basename(agent_file).replace(".json", "")
agent_config = AgentConfig.load(agent_name)
for ds in agent_config.data_sources:
if ds in source_to_agents:
source_to_agents[ds].append(agent_name)
else:
source_to_agents[ds] = [agent_name]
for data_source in StorageConnector.list_loaded_data():
location = config.archival_storage_type
agents = ",".join(source_to_agents[data_source]) if data_source in source_to_agents else ""
table.add_row([data_source, location, agents])
print(table)
else:
raise ValueError(f"Unknown option {option}")

133
memgpt/cli/cli_load.py
View File

@@ -9,11 +9,77 @@ memgpt load <data-connector-type> --name <dataset-name> [ADDITIONAL ARGS]
"""
from typing import List
from tqdm import tqdm
import typer
from memgpt.embeddings import embedding_model
from memgpt.connectors.storage import StorageConnector, Passage
from memgpt.config import MemGPTConfig
from llama_index import (
VectorStoreIndex,
ServiceContext,
StorageContext,
load_index_from_storage,
)
app = typer.Typer()
def store_docs(name, docs, show_progress=True):
"""Common function for embedding and storing documents"""
storage = StorageConnector.get_storage_connector(name=name)
config = MemGPTConfig.load()
embed_model = embedding_model()
# use llama index to run embeddings code
service_context = ServiceContext.from_defaults(llm=None, embed_model=embed_model, chunk_size=config.embedding_chunk_size)
index = VectorStoreIndex.from_documents(docs, service_context=service_context, show_progress=True)
embed_dict = index._vector_store._data.embedding_dict
node_dict = index._docstore.docs
# gather passages
passages = []
for node_id, node in tqdm(node_dict.items()):
vector = embed_dict[node_id]
node.embedding = vector
text = node.text.replace("\x00", "\uFFFD") # hacky fix for error on null characters
assert (
len(node.embedding) == config.embedding_dim
), f"Expected embedding dimension {config.embedding_dim}, got {len(node.embedding)}"
passages.append(Passage(text=text, embedding=vector))
# insert into storage
storage.insert_many(passages)
storage.save()
@app.command("index")
def load_index(
name: str = typer.Option(help="Name of dataset to load."), dir: str = typer.Option(help="Path to directory containing index.")
):
"""Load a LlamaIndex saved VectorIndex into MemGPT"""
# load index data
storage_context = StorageContext.from_defaults(persist_dir=dir)
loaded_index = load_index_from_storage(storage_context)
# hacky code to extract out passages/embeddings (thanks a lot, llama index)
embed_dict = loaded_index._vector_store._data.embedding_dict
node_dict = loaded_index._docstore.docs
passages = []
for node_id, node in node_dict.items():
vector = embed_dict[node_id]
node.embedding = vector
passages.append(Passage(text=node.text, embedding=vector))
# create storage connector
storage = StorageConnector.get_storage_connector(name=name)
# add and save all passages
storage.insert_many(passages)
storage.save()
@app.command("directory")
def load_directory(
name: str = typer.Option(help="Name of dataset to load."),
@@ -22,7 +88,6 @@ def load_directory(
recursive: bool = typer.Option(False, help="Recursively search for files in directory."),
):
from llama_index import SimpleDirectoryReader
from memgpt.utils import get_index, save_index
if recursive:
assert input_dir is not None, "Must provide input directory if recursive is True."
@@ -37,14 +102,10 @@ def load_directory(
reader = SimpleDirectoryReader(input_files=input_files)
# load docs
print("Loading data...")
print("loading data")
docs = reader.load_data()
# embed docs
print("Indexing documents...")
index = get_index(name, docs)
# save connector information into .memgpt metadata file
save_index(index, name)
print("done loading data")
store_docs(name, docs)
@app.command("webpage")
@@ -53,15 +114,9 @@ def load_webpage(
urls: List[str] = typer.Option(None, help="List of urls to load."),
):
from llama_index import SimpleWebPageReader
from memgpt.utils import get_index, save_index
docs = SimpleWebPageReader(html_to_text=True).load_data(urls)
# embed docs
print("Indexing documents...")
index = get_index(docs)
# save connector information into .memgpt metadata file
save_index(index, name)
store_docs(name, docs)
@app.command("database")
@@ -77,13 +132,12 @@ def load_database(
dbname: str = typer.Option(None, help="Database name."),
):
from llama_index.readers.database import DatabaseReader
from memgpt.utils import get_index, save_index
print(dump_path, scheme)
if dump_path is not None:
# read from database dump file
from sqlalchemy import create_engine, MetaData
from sqlalchemy import create_engine
engine = create_engine(f"sqlite:///{dump_path}")
@@ -108,6 +162,47 @@ def load_database(
# load data
docs = db.load_data(query=query)
store_docs(name, docs)
index = get_index(name, docs)
save_index(index, name)
@app.command("vector-database")
def load_vector_database(
name: str = typer.Option(help="Name of dataset to load."),
uri: str = typer.Option(help="Database URI."),
table_name: str = typer.Option(help="Name of table containing data."),
text_column: str = typer.Option(help="Name of column containing text."),
embedding_column: str = typer.Option(help="Name of column containing embedding."),
):
"""Load pre-computed embeddings into MemGPT from a database."""
from sqlalchemy import create_engine, select, MetaData, Table, Inspector
from pgvector.sqlalchemy import Vector
# connect to db table
engine = create_engine(uri)
metadata = MetaData()
# Create an inspector to inspect the database
inspector = Inspector.from_engine(engine)
table_names = inspector.get_table_names()
assert table_name in table_names, f"Table {table_name} not found in database: tables that exist {table_names}."
table = Table(table_name, metadata, autoload_with=engine)
config = MemGPTConfig.load()
# Prepare a select statement
select_statement = select(table.c[text_column], table.c[embedding_column].cast(Vector(config.embedding_dim)))
# Execute the query and fetch the results
with engine.connect() as connection:
result = connection.execute(select_statement).fetchall()
# Convert to a list of tuples (text, embedding)
passages = []
for text, embedding in result:
passages.append(Passage(text=text, embedding=embedding))
assert config.embedding_dim == len(embedding), f"Expected embedding dimension {config.embedding_dim}, got {len(embedding)}"
# insert into storage
storage = StorageConnector.get_storage_connector(name=name)
storage.insert_many(passages)

60
memgpt/config.py
View File

@@ -65,7 +65,7 @@ class MemGPTConfig:
# embedding parameters
embedding_model: str = "openai"
embedding_dim: int = 768
embedding_dim: int = 1536
embedding_chunk_size: int = 300 # number of tokens
# database configs: archival
@@ -90,8 +90,15 @@ class MemGPTConfig:
@classmethod
def load(cls) -> "MemGPTConfig":
config = configparser.ConfigParser()
if os.path.exists(MemGPTConfig.config_path):
config.read(MemGPTConfig.config_path)
# allow overriding with env variables
if os.getenv("MEMGPT_CONFIG_PATH"):
config_path = os.getenv("MEMGPT_CONFIG_PATH")
else:
config_path = MemGPTConfig.config_path
if os.path.exists(config_path):
config.read(config_path)
# read config values
model = config.get("defaults", "model")
@@ -119,6 +126,11 @@ class MemGPTConfig:
embedding_dim = config.getint("embedding", "dim")
embedding_chunk_size = config.getint("embedding", "chunk_size")
# archival storage
archival_storage_type = config.get("archival_storage", "type")
archival_storage_path = config.get("archival_storage", "path") if config.has_option("archival_storage", "path") else None
archival_storage_uri = config.get("archival_storage", "uri") if config.has_option("archival_storage", "uri") else None
anon_clientid = config.get("client", "anon_clientid")
return cls(
@@ -137,11 +149,15 @@ class MemGPTConfig:
embedding_model=embedding_model,
embedding_dim=embedding_dim,
embedding_chunk_size=embedding_chunk_size,
archival_storage_type=archival_storage_type,
archival_storage_path=archival_storage_path,
archival_storage_uri=archival_storage_uri,
anon_clientid=anon_clientid,
config_path=config_path,
)
anon_clientid = MemGPTConfig.generate_uuid()
config = cls(anon_clientid=anon_clientid)
config = cls(anon_clientid=anon_clientid, config_path=config_path)
config.save() # save updated config
return config
@@ -179,18 +195,34 @@ class MemGPTConfig:
config.set("embedding", "dim", str(self.embedding_dim))
config.set("embedding", "chunk_size", str(self.embedding_chunk_size))
# archival storage
config.add_section("archival_storage")
print("archival storage", self.archival_storage_type)
config.set("archival_storage", "type", self.archival_storage_type)
if self.archival_storage_path:
config.set("archival_storage", "path", self.archival_storage_path)
if self.archival_storage_uri:
config.set("archival_storage", "uri", self.archival_storage_uri)
# client
config.add_section("client")
if not self.anon_clientid:
self.anon_clientid = self.generate_uuid()
config.set("client", "anon_clientid", self.anon_clientid)
if not os.path.exists(MEMGPT_DIR):
os.makedirs(MEMGPT_DIR, exist_ok=True)
with open(self.config_path, "w") as f:
config.write(f)
@staticmethod
def exists():
return os.path.exists(MemGPTConfig.config_path)
# allow overriding with env variables
if os.getenv("MEMGPT_CONFIG_PATH"):
config_path = os.getenv("MEMGPT_CONFIG_PATH")
else:
config_path = MemGPTConfig.config_path
return os.path.exists(config_path)
@staticmethod
def create_config_dir():
@@ -209,7 +241,18 @@ class AgentConfig:
Configuration for a specific instance of an agent
"""
def __init__(self, persona, human, model, preset=DEFAULT_PRESET, name=None, data_source=None, agent_config_path=None, create_time=None):
def __init__(
self,
persona,
human,
model,
preset=DEFAULT_PRESET,
name=None,
data_sources=[],
agent_config_path=None,
create_time=None,
data_source=None,
):
if name is None:
self.name = f"agent_{self.generate_agent_id()}"
else:
@@ -218,8 +261,9 @@ class AgentConfig:
self.human = human
self.model = model
self.preset = preset
self.data_source = data_source
self.data_sources = data_sources
self.create_time = create_time if create_time is not None else utils.get_local_time()
self.data_source = None # deprecated
# save agent config
self.agent_config_path = (
@@ -240,7 +284,7 @@ class AgentConfig:
def attach_data_source(self, data_source: str):
# TODO: add warning that only once source can be attached
# i.e. previous source will be overriden
self.data_source = data_source
self.data_sources.append(data_source)
self.save()
def save_state_dir(self):

162
memgpt/connectors/db.py Normal file
View File

@@ -0,0 +1,162 @@
from pgvector.psycopg import register_vector
from pgvector.sqlalchemy import Vector
import psycopg
from sqlalchemy import create_engine, Column, String, BIGINT, select, inspect, text
from sqlalchemy.orm import sessionmaker, mapped_column
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.sql import func
import re
from tqdm import tqdm
from typing import Optional, List
import numpy as np
from tqdm import tqdm
from memgpt.config import MemGPTConfig
from memgpt.connectors.storage import StorageConnector, Passage
from memgpt.config import AgentConfig, MemGPTConfig
from memgpt.constants import MEMGPT_DIR
from memgpt.utils import printd
Base = declarative_base()
class PassageModel(Base):
"""Defines data model for storing Passages (consisting of text, embedding)"""
__abstract__ = True # this line is necessary
# Assuming passage_id is the primary key
id = Column(BIGINT, primary_key=True, nullable=False, autoincrement=True)
doc_id = Column(String)
text = Column(String, nullable=False)
embedding = mapped_column(Vector(1536)) # TODO: don't hard-code
# metadata_ = Column(JSON(astext_type=Text()))
def __repr__(self):
return f"<Passage(passage_id='{self.id}', text='{self.text}', embedding='{self.embedding})>"
def get_db_model(table_name: str):
"""Create database model for table_name"""
class_name = f"{table_name.capitalize()}Model"
Model = type(class_name, (PassageModel,), {"__tablename__": table_name, "__table_args__": {"extend_existing": True}})
return Model
class PostgresStorageConnector(StorageConnector):
"""Storage via Postgres"""
# TODO: this should probably eventually be moved into a parent DB class
def __init__(self, name: Optional[str] = None, agent_config: Optional[AgentConfig] = None):
config = MemGPTConfig.load()
# determine table name
if agent_config:
assert name is None, f"Cannot specify both agent config and name {name}"
self.table_name = self.generate_table_name_agent(agent_config)
elif name:
assert agent_config is None, f"Cannot specify both agent config and name {name}"
self.table_name = self.generate_table_name(name)
else:
raise ValueError("Must specify either agent config or name")
printd(f"Using table name {self.table_name}")
# create table
self.uri = config.archival_storage_uri
if config.archival_storage_uri is None:
raise ValueError(f"Must specifiy archival_storage_uri in config")
self.db_model = get_db_model(self.table_name)
self.engine = create_engine(self.uri)
Base.metadata.create_all(self.engine) # Create the table if it doesn't exist
self.Session = sessionmaker(bind=self.engine)
self.Session().execute(text("CREATE EXTENSION IF NOT EXISTS vector")) # Enables the vector extension
def get_all(self) -> List[Passage]:
session = self.Session()
db_passages = session.query(self.db_model).all()
return [Passage(text=p.text, embedding=p.embedding, doc_id=p.doc_id, passage_id=p.id) for p in db_passages]
def get(self, id: str) -> Optional[Passage]:
session = self.Session()
db_passage = session.query(self.db_model).get(id)
if db_passage is None:
return None
return Passage(text=db_passage.text, embedding=db_passage.embedding, doc_id=db_passage.doc_id, passage_id=db_passage.passage_id)
def insert(self, passage: Passage):
session = self.Session()
db_passage = self.db_model(doc_id=passage.doc_id, text=passage.text, embedding=passage.embedding)
session.add(db_passage)
session.commit()
def insert_many(self, passages: List[Passage], show_progress=True):
session = self.Session()
iterable = tqdm(passages) if show_progress else passages
for passage in iterable:
db_passage = self.db_model(doc_id=passage.doc_id, text=passage.text, embedding=passage.embedding)
session.add(db_passage)
session.commit()
def query(self, query: str, query_vec: List[float], top_k: int = 10) -> List[Passage]:
session = self.Session()
# Assuming PassageModel.embedding has the capability of computing l2_distance
results = session.scalars(select(self.db_model).order_by(self.db_model.embedding.l2_distance(query_vec)).limit(top_k)).all()
# Convert the results into Passage objects
passages = [
Passage(text=result.text, embedding=np.frombuffer(result.embedding), doc_id=result.doc_id, passage_id=result.id)
for result in results
]
return passages
def delete(self):
"""Drop the passage table from the database."""
# Bind the engine to the metadata of the base class so that the
# declaratives can be accessed through a DBSession instance
Base.metadata.bind = self.engine
# Drop the table specified by the PassageModel class
self.db_model.__table__.drop(self.engine)
def save(self):
# don't need to save
print("Saving db")
return
@staticmethod
def list_loaded_data():
config = MemGPTConfig.load()
engine = create_engine(config.archival_storage_uri)
inspector = inspect(engine)
tables = inspector.get_table_names()
tables = [table for table in tables if table.startswith("memgpt_") and not table.startswith("memgpt_agent_")]
tables = [table.replace("memgpt_", "") for table in tables]
return tables
def sanitize_table_name(self, name: str) -> str:
# Remove leading and trailing whitespace
name = name.strip()
# Replace spaces and invalid characters with underscores
name = re.sub(r"\s+|\W+", "_", name)
# Truncate to the maximum identifier length (e.g., 63 for PostgreSQL)
max_length = 63
if len(name) > max_length:
name = name[:max_length].rstrip("_")
# Convert to lowercase
name = name.lower()
return name
def generate_table_name_agent(self, agent_config: AgentConfig):
return f"memgpt_agent_{self.sanitize_table_name(agent_config.name)}"
def generate_table_name(self, name: str):
return f"memgpt_{self.sanitize_table_name(name)}"

132
memgpt/connectors/local.py Normal file
View File

@@ -0,0 +1,132 @@
from typing import Optional, List
from memgpt.config import AgentConfig, MemGPTConfig
from tqdm import tqdm
import re
import pickle
import os
from typing import List, Optional
from llama_index import (
VectorStoreIndex,
EmptyIndex,
ServiceContext,
)
from llama_index.retrievers import VectorIndexRetriever
from llama_index.schema import TextNode
from memgpt.constants import MEMGPT_DIR
from memgpt.config import MemGPTConfig
from memgpt.connectors.storage import StorageConnector, Passage
from memgpt.config import AgentConfig, MemGPTConfig
class LocalStorageConnector(StorageConnector):
"""Local storage connector based on LlamaIndex"""
def __init__(self, name: Optional[str] = None, agent_config: Optional[AgentConfig] = None):
from memgpt.embeddings import embedding_model
config = MemGPTConfig.load()
# TODO: add asserts to avoid both being passed
if name is None:
self.name = agent_config.name
self.save_directory = agent_config.save_agent_index_dir()
else:
self.name = name
self.save_directory = f"{MEMGPT_DIR}/archival/{name}"
# llama index contexts
self.embed_model = embedding_model()
self.service_context = ServiceContext.from_defaults(llm=None, embed_model=self.embed_model, chunk_size=config.embedding_chunk_size)
# load/create index
self.save_path = f"{self.save_directory}/nodes.pkl"
if os.path.exists(self.save_path):
self.nodes = pickle.load(open(self.save_path, "rb"))
else:
self.nodes = []
# create vectorindex
if len(self.nodes):
self.index = VectorStoreIndex(self.nodes)
else:
self.index = EmptyIndex()
def get_nodes(self) -> List[TextNode]:
"""Get llama index nodes"""
embed_dict = self.index._vector_store._data.embedding_dict
node_dict = self.index._docstore.docs
nodes = []
for node_id, node in node_dict.items():
vector = embed_dict[node_id]
node.embedding = vector
nodes.append(TextNode(text=node.text, embedding=vector))
return nodes
def add_nodes(self, nodes: List[TextNode]):
self.nodes += nodes
self.index = VectorStoreIndex(self.nodes)
def get_all(self) -> List[Passage]:
passages = []
for node in self.get_nodes():
assert node.embedding is not None, f"Node embedding is None"
passages.append(Passage(text=node.text, embedding=node.embedding))
return passages
def get(self, id: str) -> Passage:
pass
def insert(self, passage: Passage):
nodes = [TextNode(text=passage.text, embedding=passage.embedding)]
print("nodes", nodes)
self.nodes += nodes
if isinstance(self.index, EmptyIndex):
self.index = VectorStoreIndex(self.nodes, service_context=self.service_context, show_progress=True)
else:
self.index.insert_nodes(nodes)
def insert_many(self, passages: List[Passage]):
nodes = [TextNode(text=passage.text, embedding=passage.embedding) for passage in passages]
self.nodes += nodes
if isinstance(self.index, EmptyIndex):
self.index = VectorStoreIndex(self.nodes, service_context=self.service_context, show_progress=True)
print("new size", len(self.get_nodes()))
else:
orig_size = len(self.get_nodes())
self.index.insert_nodes(nodes)
assert len(self.get_nodes()) == orig_size + len(
passages
), f"expected {orig_size + len(passages)} nodes, got {len(self.get_nodes())} nodes"
def query(self, query: str, query_vec: List[float], top_k: int = 10) -> List[Passage]:
# TODO: this may be super slow?
# the nice thing about creating this here is that now we can save the persistent storage manager
retriever = VectorIndexRetriever(
index=self.index, # does this get refreshed?
similarity_top_k=top_k,
)
nodes = retriever.retrieve(query)
results = [Passage(embedding=node.embedding, text=node.text) for node in nodes]
print(results)
return results
def save(self):
# assert len(self.nodes) == len(self.get_nodes()), f"Expected {len(self.nodes)} nodes, got {len(self.get_nodes())} nodes"
self.nodes = self.get_nodes()
os.makedirs(self.save_directory, exist_ok=True)
pickle.dump(self.nodes, open(self.save_path, "wb"))
print("Saved local", self.save_path)
@staticmethod
def list_loaded_data():
sources = []
for data_source_file in os.listdir(os.path.join(MEMGPT_DIR, "archival")):
name = os.path.basename(data_source_file)
sources.append(name)
return sources

86
memgpt/connectors/storage.py Normal file
View File

@@ -0,0 +1,86 @@
""" These classes define storage connectors.
We originally tried to use Llama Index VectorIndex, but their limited API was extremely problematic.
"""
from typing import Optional, List
import re
import pickle
import os
from typing import List, Optional
from abc import abstractmethod
import numpy as np
from tqdm import tqdm
from memgpt.config import AgentConfig, MemGPTConfig
class Passage:
"""A passage is a single unit of memory, and a standard format accross all storage backends.
It is a string of text with an associated embedding.
"""
def __init__(self, text: str, embedding: np.ndarray, doc_id: Optional[str] = None, passage_id: Optional[str] = None):
self.text = text
self.embedding = embedding
self.doc_id = doc_id
self.passage_id = passage_id
def __repr__(self):
return f"Passage(text={self.text}, embedding={self.embedding})"
class StorageConnector:
@staticmethod
def get_storage_connector(name: Optional[str] = None, agent_config: Optional[AgentConfig] = None):
from memgpt.connectors.db import PostgresStorageConnector
from memgpt.connectors.local import LocalStorageConnector
storage_type = MemGPTConfig.load().archival_storage_type
if storage_type == "local":
return LocalStorageConnector(name=name, agent_config=agent_config)
elif storage_type == "postgres":
return PostgresStorageConnector(name=name, agent_config=agent_config)
else:
raise NotImplementedError(f"Storage type {storage_type} not implemented")
@staticmethod
def list_loaded_data():
from memgpt.connectors.db import PostgresStorageConnector
from memgpt.connectors.local import LocalStorageConnector
storage_type = MemGPTConfig.load().archival_storage_type
if storage_type == "local":
return LocalStorageConnector.list_loaded_data()
elif storage_type == "postgres":
return PostgresStorageConnector.list_loaded_data()
else:
raise NotImplementedError(f"Storage type {storage_type} not implemented")
@abstractmethod
def get_all(self) -> List[Passage]:
pass
@abstractmethod
def get(self, id: str) -> Passage:
pass
@abstractmethod
def insert(self, passage: Passage):
pass
@abstractmethod
def insert_many(self, passages: List[Passage]):
pass
@abstractmethod
def query(self, query: str, query_vec: List[float], top_k: int = 10) -> List[Passage]:
pass
@abstractmethod
def save(self):
"""Save state of storage connector"""
pass

10
memgpt/embeddings.py
View File

@@ -1,9 +1,15 @@
from memgpt.config import MemGPTConfig
import typer
from llama_index.embeddings import OpenAIEmbedding
def embedding_model(config: MemGPTConfig):
def embedding_model():
"""Return LlamaIndex embedding model to use for embeddings"""
from memgpt.config import MemGPTConfig
# load config
config = MemGPTConfig.load()
# TODO: use embedding_endpoint in the future
if config.model_endpoint == "openai":
return OpenAIEmbedding()

36
memgpt/main.py
View File

@@ -31,7 +31,7 @@ from memgpt.persistence_manager import (
InMemoryStateManagerWithPreloadedArchivalMemory,
InMemoryStateManagerWithFaiss,
)
from memgpt.cli.cli import run
from memgpt.cli.cli import run, attach
from memgpt.cli.cli_config import configure, list, add
from memgpt.cli.cli_load import app as load_app
from memgpt.config import Config, MemGPTConfig, AgentConfig
@@ -42,10 +42,12 @@ from memgpt.openai_tools import (
check_azure_embeddings,
get_set_azure_env_vars,
)
from memgpt.connectors.storage import StorageConnector
import asyncio
app = typer.Typer()
app.command(name="run")(run)
app.command(name="attach")(attach)
app.command(name="configure")(configure)
app.command(name="list")(list)
app.command(name="add")(add)
@@ -410,7 +412,12 @@ async def run_agent_loop(memgpt_agent, first, no_verify=False, cfg=None, strip_u
if user_input.startswith("/"):
if legacy:
# legacy agent save functions (TODO: eventually remove)
if user_input.lower() == "/exit":
if user_input.lower() == "/load" or user_input.lower().startswith("/load "):
command = user_input.strip().split()
filename = command[1] if len(command) > 1 else None
load(memgpt_agent=memgpt_agent, filename=filename)
continue
elif user_input.lower() == "/exit":
# autosave
save(memgpt_agent=memgpt_agent, cfg=cfg)
break
@@ -441,10 +448,26 @@ async def run_agent_loop(memgpt_agent, first, no_verify=False, cfg=None, strip_u
memgpt_agent.save()
continue
if user_input.lower() == "/load" or user_input.lower().startswith("/load "):
command = user_input.strip().split()
filename = command[1] if len(command) > 1 else None
load(memgpt_agent=memgpt_agent, filename=filename)
if user_input.lower() == "/attach":
if legacy:
typer.secho("Error: /attach is not supported in legacy mode.", fg=typer.colors.RED, bold=True)
continue
# TODO: check if agent already has it
data_source_options = StorageConnector.list_loaded_data()
data_source = await questionary.select("Select data source", choices=data_source_options).ask_async()
# attach new data
attach(memgpt_agent.config.name, data_source)
# update agent config
memgpt_agent.config.attach_data_source(data_source)
# reload agent with new data source
# TODO: maybe make this less ugly...
memgpt_agent.persistence_manager.archival_memory.storage = StorageConnector.get_storage_connector(
agent_config=memgpt_agent.config
)
continue
elif user_input.lower() == "/dump":
@@ -565,6 +588,7 @@ USER_COMMANDS = [
("/pop", "undo the last message in the conversation"),
("/heartbeat", "send a heartbeat system message to the agent"),
("/memorywarning", "send a memory warning system message to the agent"),
("/attach", "attach data source to agent"),
]
# if __name__ == "__main__":
#

134
memgpt/memory.py
View File

@@ -22,11 +22,20 @@ from llama_index import (
get_response_synthesizer,
load_index_from_storage,
StorageContext,
Document,
)
from llama_index.node_parser import SimpleNodeParser
from llama_index.node_parser import SimpleNodeParser
from llama_index.retrievers import VectorIndexRetriever
from llama_index.query_engine import RetrieverQueryEngine
from llama_index.indices.postprocessor import SimilarityPostprocessor
from memgpt.embeddings import embedding_model
from memgpt.config import MemGPTConfig
from memgpt.embeddings import embedding_model
from memgpt.config import MemGPTConfig
class CoreMemory(object):
"""Held in-context inside the system message
@@ -172,11 +181,6 @@ async def a_summarize_messages(
class ArchivalMemory(ABC):
@abstractmethod
def __len__(self):
"""Define the length of the object. Must be implemented by subclasses."""
pass
@abstractmethod
def insert(self, memory_string):
"""Insert new archival memory
@@ -387,7 +391,7 @@ class DummyArchivalMemoryWithFaiss(DummyArchivalMemory):
async def a_insert(self, memory_string, embedding=None):
if embedding is None:
# Get the embedding
embedding = await async_get_embedding_with_backoff(memory_string, model=self.embedding_model)
embedding = async_get_embedding_with_backoff(memory_string, model=self.embedding_model)
return self._insert(memory_string, embedding)
def _search(self, query_embedding, query_string, count=None, start=None):
@@ -444,11 +448,6 @@ class DummyArchivalMemoryWithFaiss(DummyArchivalMemory):
class RecallMemory(ABC):
@abstractmethod
def __len__(self):
"""Define the length of the object. Must be implemented by subclasses."""
pass
@abstractmethod
def text_search(self, query_string, count=None, start=None):
pass
@@ -662,10 +661,11 @@ class LocalArchivalMemory(ArchivalMemory):
self.agent_config = agent_config
# locate saved index
if self.agent_config.data_source is not None: # connected data source
directory = os.path.join(MEMGPT_DIR, "archival", self.agent_config.data_source)
assert os.path.exists(directory), f"Archival memory database {self.agent_config.data_source} does not exist"
elif self.agent_config.name is not None:
# if self.agent_config.data_source is not None: # connected data source
# directory = f"{MEMGPT_DIR}/archival/{self.agent_config.data_source}"
# assert os.path.exists(directory), f"Archival memory database {self.agent_config.data_source} does not exist"
# elif self.agent_config.name is not None:
if self.agent_config.name is not None:
directory = agent_config.save_agent_index_dir()
if not os.path.exists(directory):
# no existing archival storage
@@ -690,17 +690,15 @@ class LocalArchivalMemory(ArchivalMemory):
# TODO: have some mechanism for cleanup otherwise will lead to OOM
self.cache = {}
def __len__(self):
# TODO FIXME
return 1
def save(self):
"""Save the index to disk"""
if self.agent_config.data_source: # update original archival index
# TODO: this corrupts the originally loaded data. do we want to do this?
utils.save_index(self.index, self.agent_config.data_source)
else:
utils.save_agent_index(self.index, self.agent_config)
# if self.agent_config.data_sources: # update original archival index
# # TODO: this corrupts the originally loaded data. do we want to do this?
# utils.save_index(self.index, self.agent_config.data_sources)
# else:
# don't need to save data source, since we assume data source data is already loaded into the agent index
utils.save_agent_index(self.index, self.agent_config)
def insert(self, memory_string):
self.index.insert(memory_string)
@@ -715,6 +713,7 @@ class LocalArchivalMemory(ArchivalMemory):
return self.insert(memory_string)
def search(self, query_string, count=None, start=None):
print("searching with local")
if self.retriever is None:
print("Warning: archival memory is empty")
return [], 0
@@ -741,3 +740,90 @@ class LocalArchivalMemory(ArchivalMemory):
else:
memory_str = self.index.ref_doc_info
return f"\n### ARCHIVAL MEMORY ###" + f"\n{memory_str}"
class EmbeddingArchivalMemory(ArchivalMemory):
"""Archival memory with embedding based search"""
def __init__(self, agent_config, top_k: Optional[int] = 100):
"""Init function for archival memory
:param archiva_memory_database: name of dataset to pre-fill archival with
:type archival_memory_database: str
"""
from memgpt.connectors.storage import StorageConnector
self.top_k = top_k
self.agent_config = agent_config
config = MemGPTConfig.load()
# create embedding model
self.embed_model = embedding_model()
self.embedding_chunk_size = config.embedding_chunk_size
# create storage backend
self.storage = StorageConnector.get_storage_connector(agent_config=agent_config)
# TODO: have some mechanism for cleanup otherwise will lead to OOM
self.cache = {}
def save(self):
"""Save the index to disk"""
self.storage.save()
def insert(self, memory_string):
"""Embed and save memory string"""
from memgpt.connectors.storage import Passage
try:
passages = []
# create parser
parser = SimpleNodeParser.from_defaults(chunk_size=self.embedding_chunk_size)
# breakup string into passages
for node in parser.get_nodes_from_documents([Document(text=memory_string)]):
embedding = self.embed_model.get_text_embedding(node.text)
passages.append(Passage(text=node.text, embedding=embedding, doc_id=f"agent_{self.agent_config.name}_memory"))
# insert passages
self.storage.insert_many(passages)
return True
except Exception as e:
print("Archival insert error", e)
raise e
def search(self, query_string, count=None, start=None):
"""Search query string"""
try:
if query_string not in self.cache:
# self.cache[query_string] = self.retriever.retrieve(query_string)
query_vec = self.embed_model.get_text_embedding(query_string)
self.cache[query_string] = self.storage.query(query_string, query_vec, top_k=self.top_k)
start = start if start else 0
count = count if count else self.top_k
end = min(count + start, len(self.cache[query_string]))
results = self.cache[query_string][start:end]
results = [{"timestamp": get_local_time(), "content": node.text} for node in results]
return results, len(results)
except Exception as e:
print("Archival search error", e)
raise e
async def a_search(self, query_string, count=None, start=None):
return self.search(query_string, count, start)
async def a_insert(self, memory_string, embedding=None):
return self.insert(memory_string)
def __repr__(self) -> str:
limit = 10
passages = []
for passage in list(self.storage.get_all())[:limit]: # TODO: only get first 10
passages.append(str(passage.text))
memory_str = "\n".join(passages)
return f"\n### ARCHIVAL MEMORY ###" + f"\n{memory_str}"
def __len__(self):
return len(self.storage.get_all())

36
memgpt/persistence_manager.py
View File

@@ -8,7 +8,7 @@ from .memory import (
DummyArchivalMemory,
DummyArchivalMemoryWithEmbeddings,
DummyArchivalMemoryWithFaiss,
LocalArchivalMemory,
EmbeddingArchivalMemory,
)
from .utils import get_local_time, printd
@@ -106,34 +106,44 @@ class LocalStateManager(PersistenceManager):
"""In-memory state manager has nothing to manage, all agents are held in-memory"""
recall_memory_cls = DummyRecallMemory
archival_memory_cls = LocalArchivalMemory
archival_memory_cls = EmbeddingArchivalMemory
def __init__(self, agent_config: AgentConfig):
# Memory held in-state useful for debugging stateful versions
self.memory = None
self.messages = []
self.all_messages = []
self.archival_memory = LocalArchivalMemory(agent_config=agent_config)
self.archival_memory = EmbeddingArchivalMemory(agent_config)
self.recall_memory = None
self.agent_config = agent_config
@staticmethod
def load(filename, agent_config: AgentConfig):
@classmethod
def load(cls, filename, agent_config: AgentConfig):
""" Load a LocalStateManager from a file. """ ""
with open(filename, "rb") as f:
manager = pickle.load(f)
data = pickle.load(f)
manager.archival_memory = LocalArchivalMemory(agent_config=agent_config)
manager = cls(agent_config)
manager.all_messages = data["all_messages"]
manager.messages = data["messages"]
manager.recall_memory = data["recall_memory"]
manager.archival_memory = EmbeddingArchivalMemory(agent_config)
return manager
def save(self, filename):
with open(filename, "wb") as fh:
# TODO: fix this hacky solution to pickle the retriever
## TODO: fix this hacky solution to pickle the retriever
self.archival_memory.save()
self.archival_memory = None
pickle.dump(self, fh, protocol=pickle.HIGHEST_PROTOCOL)
# re-load archival (TODO: dont do this)
self.archival_memory = LocalArchivalMemory(agent_config=self.agent_config)
pickle.dump(
{
"recall_memory": self.recall_memory,
"messages": self.messages,
"all_messages": self.all_messages,
},
fh,
protocol=pickle.HIGHEST_PROTOCOL,
)
printd(f"Saved state to {fh}")
def init(self, agent):
printd(f"Initializing InMemoryStateManager with agent object")

88
memgpt/utils.py
View File

@@ -363,94 +363,6 @@ def estimate_openai_cost(docs):
return cost
def get_index(name, docs):
"""Index documents
:param docs: Documents to be embedded
:type docs: List[Document]
"""
from memgpt.config import MemGPTConfig # avoid circular import
from memgpt.embeddings import embedding_model # avoid circular import
# TODO: configure to work for local
print("Warning: get_index(docs) only supported for OpenAI")
# check if directory exists
dir = os.path.join(MEMGPT_DIR, "archival", name)
if os.path.exists(dir):
confirm = typer.confirm(typer.style(f"Index with name {name} already exists -- re-index?", fg="yellow"), default=False)
if not confirm:
# return existing index
storage_context = StorageContext.from_defaults(persist_dir=dir)
return load_index_from_storage(storage_context)
# TODO: support configurable embeddings
# TODO: read from config how to index (open ai vs. local): then embed_mode="local"
estimated_cost = estimate_openai_cost(docs)
# TODO: prettier cost formatting
confirm = typer.confirm(
typer.style(f"Open AI embedding cost will be approximately ${estimated_cost} - continue?", fg="yellow"), default=True
)
if not confirm:
typer.secho("Aborting.", fg="red")
exit()
# read embedding confirguration
# TODO: in the future, make an IngestData class that loads the config once
config = MemGPTConfig.load()
embed_model = embedding_model(config)
chunk_size = config.embedding_chunk_size
service_context = ServiceContext.from_defaults(embed_model=embed_model, chunk_size=chunk_size)
set_global_service_context(service_context)
# index documents
index = VectorStoreIndex.from_documents(docs)
return index
def save_agent_index(index, agent_config):
"""Save agent index inside of ~/.memgpt/agents/<agent_name>
:param index: Index to save
:type index: VectorStoreIndex
:param agent_name: Name of agent that the archival memory belonds to
:type agent_name: str
"""
dir = agent_config.save_agent_index_dir()
os.makedirs(dir, exist_ok=True)
index.storage_context.persist(dir)
def save_index(index, name):
"""Save index ~/.memgpt/archival/<name> to load into agents
:param index: Index to save
:type index: VectorStoreIndex
:param name: Name of index
:type name: str
"""
# save
# TODO: load directory from config
# TODO: save to vectordb/local depending on config
dir = os.path.join(MEMGPT_DIR, "archival", name)
## Avoid overwriting
## check if directory exists
# if os.path.exists(dir):
# confirm = typer.confirm(typer.style(f"Index with name {name} already exists -- overwrite?", fg="red"), default=False)
# if not confirm:
# typer.secho("Aborting.", fg="red")
# exit()
# create directory, even if it already exists
os.makedirs(dir, exist_ok=True)
index.storage_context.persist(dir)
print(dir)
def list_agent_config_files():
"""List all agents config files"""
return os.listdir(os.path.join(MEMGPT_DIR, "agents"))

597
poetry.lock generated
View File

@@ -261,102 +261,102 @@ files = [
[[package]]
name = "charset-normalizer"
version = "3.3.1"
version = "3.3.2"
description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
category = "main"
optional = false
python-versions = ">=3.7.0"
files = [
{file = "charset-normalizer-3.3.1.tar.gz", hash = "sha256:d9137a876020661972ca6eec0766d81aef8a5627df628b664b234b73396e727e"},
{file = "charset_normalizer-3.3.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:8aee051c89e13565c6bd366813c386939f8e928af93c29fda4af86d25b73d8f8"},
{file = "charset_normalizer-3.3.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:352a88c3df0d1fa886562384b86f9a9e27563d4704ee0e9d56ec6fcd270ea690"},
{file = "charset_normalizer-3.3.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:223b4d54561c01048f657fa6ce41461d5ad8ff128b9678cfe8b2ecd951e3f8a2"},
{file = "charset_normalizer-3.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4f861d94c2a450b974b86093c6c027888627b8082f1299dfd5a4bae8e2292821"},
{file = "charset_normalizer-3.3.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1171ef1fc5ab4693c5d151ae0fdad7f7349920eabbaca6271f95969fa0756c2d"},
{file = "charset_normalizer-3.3.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28f512b9a33235545fbbdac6a330a510b63be278a50071a336afc1b78781b147"},
{file = "charset_normalizer-3.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c0e842112fe3f1a4ffcf64b06dc4c61a88441c2f02f373367f7b4c1aa9be2ad5"},
{file = "charset_normalizer-3.3.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3f9bc2ce123637a60ebe819f9fccc614da1bcc05798bbbaf2dd4ec91f3e08846"},
{file = "charset_normalizer-3.3.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:f194cce575e59ffe442c10a360182a986535fd90b57f7debfaa5c845c409ecc3"},
{file = "charset_normalizer-3.3.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:9a74041ba0bfa9bc9b9bb2cd3238a6ab3b7618e759b41bd15b5f6ad958d17605"},
{file = "charset_normalizer-3.3.1-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:b578cbe580e3b41ad17b1c428f382c814b32a6ce90f2d8e39e2e635d49e498d1"},
{file = "charset_normalizer-3.3.1-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:6db3cfb9b4fcecb4390db154e75b49578c87a3b9979b40cdf90d7e4b945656e1"},
{file = "charset_normalizer-3.3.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:debb633f3f7856f95ad957d9b9c781f8e2c6303ef21724ec94bea2ce2fcbd056"},
{file = "charset_normalizer-3.3.1-cp310-cp310-win32.whl", hash = "sha256:87071618d3d8ec8b186d53cb6e66955ef2a0e4fa63ccd3709c0c90ac5a43520f"},
{file = "charset_normalizer-3.3.1-cp310-cp310-win_amd64.whl", hash = "sha256:e372d7dfd154009142631de2d316adad3cc1c36c32a38b16a4751ba78da2a397"},
{file = "charset_normalizer-3.3.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:ae4070f741f8d809075ef697877fd350ecf0b7c5837ed68738607ee0a2c572cf"},
{file = "charset_normalizer-3.3.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:58e875eb7016fd014c0eea46c6fa92b87b62c0cb31b9feae25cbbe62c919f54d"},
{file = "charset_normalizer-3.3.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:dbd95e300367aa0827496fe75a1766d198d34385a58f97683fe6e07f89ca3e3c"},
{file = "charset_normalizer-3.3.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:de0b4caa1c8a21394e8ce971997614a17648f94e1cd0640fbd6b4d14cab13a72"},
{file = "charset_normalizer-3.3.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:985c7965f62f6f32bf432e2681173db41336a9c2611693247069288bcb0c7f8b"},
{file = "charset_normalizer-3.3.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a15c1fe6d26e83fd2e5972425a772cca158eae58b05d4a25a4e474c221053e2d"},
{file = "charset_normalizer-3.3.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ae55d592b02c4349525b6ed8f74c692509e5adffa842e582c0f861751701a673"},
{file = "charset_normalizer-3.3.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:be4d9c2770044a59715eb57c1144dedea7c5d5ae80c68fb9959515037cde2008"},
{file = "charset_normalizer-3.3.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:851cf693fb3aaef71031237cd68699dded198657ec1e76a76eb8be58c03a5d1f"},
{file = "charset_normalizer-3.3.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:31bbaba7218904d2eabecf4feec0d07469284e952a27400f23b6628439439fa7"},
{file = "charset_normalizer-3.3.1-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:871d045d6ccc181fd863a3cd66ee8e395523ebfbc57f85f91f035f50cee8e3d4"},
{file = "charset_normalizer-3.3.1-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:501adc5eb6cd5f40a6f77fbd90e5ab915c8fd6e8c614af2db5561e16c600d6f3"},
{file = "charset_normalizer-3.3.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:f5fb672c396d826ca16a022ac04c9dce74e00a1c344f6ad1a0fdc1ba1f332213"},
{file = "charset_normalizer-3.3.1-cp311-cp311-win32.whl", hash = "sha256:bb06098d019766ca16fc915ecaa455c1f1cd594204e7f840cd6258237b5079a8"},
{file = "charset_normalizer-3.3.1-cp311-cp311-win_amd64.whl", hash = "sha256:8af5a8917b8af42295e86b64903156b4f110a30dca5f3b5aedea123fbd638bff"},
{file = "charset_normalizer-3.3.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:7ae8e5142dcc7a49168f4055255dbcced01dc1714a90a21f87448dc8d90617d1"},
{file = "charset_normalizer-3.3.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:5b70bab78accbc672f50e878a5b73ca692f45f5b5e25c8066d748c09405e6a55"},
{file = "charset_normalizer-3.3.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:5ceca5876032362ae73b83347be8b5dbd2d1faf3358deb38c9c88776779b2e2f"},
{file = "charset_normalizer-3.3.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:34d95638ff3613849f473afc33f65c401a89f3b9528d0d213c7037c398a51296"},
{file = "charset_normalizer-3.3.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9edbe6a5bf8b56a4a84533ba2b2f489d0046e755c29616ef8830f9e7d9cf5728"},
{file = "charset_normalizer-3.3.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f6a02a3c7950cafaadcd46a226ad9e12fc9744652cc69f9e5534f98b47f3bbcf"},
{file = "charset_normalizer-3.3.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:10b8dd31e10f32410751b3430996f9807fc4d1587ca69772e2aa940a82ab571a"},
{file = "charset_normalizer-3.3.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:edc0202099ea1d82844316604e17d2b175044f9bcb6b398aab781eba957224bd"},
{file = "charset_normalizer-3.3.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:b891a2f68e09c5ef989007fac11476ed33c5c9994449a4e2c3386529d703dc8b"},
{file = "charset_normalizer-3.3.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:71ef3b9be10070360f289aea4838c784f8b851be3ba58cf796262b57775c2f14"},
{file = "charset_normalizer-3.3.1-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:55602981b2dbf8184c098bc10287e8c245e351cd4fdcad050bd7199d5a8bf514"},
{file = "charset_normalizer-3.3.1-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:46fb9970aa5eeca547d7aa0de5d4b124a288b42eaefac677bde805013c95725c"},
{file = "charset_normalizer-3.3.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:520b7a142d2524f999447b3a0cf95115df81c4f33003c51a6ab637cbda9d0bf4"},
{file = "charset_normalizer-3.3.1-cp312-cp312-win32.whl", hash = "sha256:8ec8ef42c6cd5856a7613dcd1eaf21e5573b2185263d87d27c8edcae33b62a61"},
{file = "charset_normalizer-3.3.1-cp312-cp312-win_amd64.whl", hash = "sha256:baec8148d6b8bd5cee1ae138ba658c71f5b03e0d69d5907703e3e1df96db5e41"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:63a6f59e2d01310f754c270e4a257426fe5a591dc487f1983b3bbe793cf6bac6"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1d6bfc32a68bc0933819cfdfe45f9abc3cae3877e1d90aac7259d57e6e0f85b1"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4f3100d86dcd03c03f7e9c3fdb23d92e32abbca07e7c13ebd7ddfbcb06f5991f"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:39b70a6f88eebe239fa775190796d55a33cfb6d36b9ffdd37843f7c4c1b5dc67"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4e12f8ee80aa35e746230a2af83e81bd6b52daa92a8afaef4fea4a2ce9b9f4fa"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7b6cefa579e1237ce198619b76eaa148b71894fb0d6bcf9024460f9bf30fd228"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:61f1e3fb621f5420523abb71f5771a204b33c21d31e7d9d86881b2cffe92c47c"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:4f6e2a839f83a6a76854d12dbebde50e4b1afa63e27761549d006fa53e9aa80e"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:1ec937546cad86d0dce5396748bf392bb7b62a9eeb8c66efac60e947697f0e58"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:82ca51ff0fc5b641a2d4e1cc8c5ff108699b7a56d7f3ad6f6da9dbb6f0145b48"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:633968254f8d421e70f91c6ebe71ed0ab140220469cf87a9857e21c16687c034"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-win32.whl", hash = "sha256:c0c72d34e7de5604df0fde3644cc079feee5e55464967d10b24b1de268deceb9"},
{file = "charset_normalizer-3.3.1-cp37-cp37m-win_amd64.whl", hash = "sha256:63accd11149c0f9a99e3bc095bbdb5a464862d77a7e309ad5938fbc8721235ae"},
{file = "charset_normalizer-3.3.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5a3580a4fdc4ac05f9e53c57f965e3594b2f99796231380adb2baaab96e22761"},
{file = "charset_normalizer-3.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:2465aa50c9299d615d757c1c888bc6fef384b7c4aec81c05a0172b4400f98557"},
{file = "charset_normalizer-3.3.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cb7cd68814308aade9d0c93c5bd2ade9f9441666f8ba5aa9c2d4b389cb5e2a45"},
{file = "charset_normalizer-3.3.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:91e43805ccafa0a91831f9cd5443aa34528c0c3f2cc48c4cb3d9a7721053874b"},
{file = "charset_normalizer-3.3.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:854cc74367180beb327ab9d00f964f6d91da06450b0855cbbb09187bcdb02de5"},
{file = "charset_normalizer-3.3.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c15070ebf11b8b7fd1bfff7217e9324963c82dbdf6182ff7050519e350e7ad9f"},
{file = "charset_normalizer-3.3.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c4c99f98fc3a1835af8179dcc9013f93594d0670e2fa80c83aa36346ee763d2"},
{file = "charset_normalizer-3.3.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3fb765362688821404ad6cf86772fc54993ec11577cd5a92ac44b4c2ba52155b"},
{file = "charset_normalizer-3.3.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:dced27917823df984fe0c80a5c4ad75cf58df0fbfae890bc08004cd3888922a2"},
{file = "charset_normalizer-3.3.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a66bcdf19c1a523e41b8e9d53d0cedbfbac2e93c649a2e9502cb26c014d0980c"},
{file = "charset_normalizer-3.3.1-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:ecd26be9f112c4f96718290c10f4caea6cc798459a3a76636b817a0ed7874e42"},
{file = "charset_normalizer-3.3.1-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:3f70fd716855cd3b855316b226a1ac8bdb3caf4f7ea96edcccc6f484217c9597"},
{file = "charset_normalizer-3.3.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:17a866d61259c7de1bdadef418a37755050ddb4b922df8b356503234fff7932c"},
{file = "charset_normalizer-3.3.1-cp38-cp38-win32.whl", hash = "sha256:548eefad783ed787b38cb6f9a574bd8664468cc76d1538215d510a3cd41406cb"},
{file = "charset_normalizer-3.3.1-cp38-cp38-win_amd64.whl", hash = "sha256:45f053a0ece92c734d874861ffe6e3cc92150e32136dd59ab1fb070575189c97"},
{file = "charset_normalizer-3.3.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:bc791ec3fd0c4309a753f95bb6c749ef0d8ea3aea91f07ee1cf06b7b02118f2f"},
{file = "charset_normalizer-3.3.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:0c8c61fb505c7dad1d251c284e712d4e0372cef3b067f7ddf82a7fa82e1e9a93"},
{file = "charset_normalizer-3.3.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:2c092be3885a1b7899cd85ce24acedc1034199d6fca1483fa2c3a35c86e43041"},
{file = "charset_normalizer-3.3.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c2000c54c395d9e5e44c99dc7c20a64dc371f777faf8bae4919ad3e99ce5253e"},
{file = "charset_normalizer-3.3.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4cb50a0335382aac15c31b61d8531bc9bb657cfd848b1d7158009472189f3d62"},
{file = "charset_normalizer-3.3.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c30187840d36d0ba2893bc3271a36a517a717f9fd383a98e2697ee890a37c273"},
{file = "charset_normalizer-3.3.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fe81b35c33772e56f4b6cf62cf4aedc1762ef7162a31e6ac7fe5e40d0149eb67"},
{file = "charset_normalizer-3.3.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d0bf89afcbcf4d1bb2652f6580e5e55a840fdf87384f6063c4a4f0c95e378656"},
{file = "charset_normalizer-3.3.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:06cf46bdff72f58645434d467bf5228080801298fbba19fe268a01b4534467f5"},
{file = "charset_normalizer-3.3.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:3c66df3f41abee950d6638adc7eac4730a306b022570f71dd0bd6ba53503ab57"},
{file = "charset_normalizer-3.3.1-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:cd805513198304026bd379d1d516afbf6c3c13f4382134a2c526b8b854da1c2e"},
{file = "charset_normalizer-3.3.1-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:9505dc359edb6a330efcd2be825fdb73ee3e628d9010597aa1aee5aa63442e97"},
{file = "charset_normalizer-3.3.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:31445f38053476a0c4e6d12b047b08ced81e2c7c712e5a1ad97bc913256f91b2"},
{file = "charset_normalizer-3.3.1-cp39-cp39-win32.whl", hash = "sha256:bd28b31730f0e982ace8663d108e01199098432a30a4c410d06fe08fdb9e93f4"},
{file = "charset_normalizer-3.3.1-cp39-cp39-win_amd64.whl", hash = "sha256:555fe186da0068d3354cdf4bbcbc609b0ecae4d04c921cc13e209eece7720727"},
{file = "charset_normalizer-3.3.1-py3-none-any.whl", hash = "sha256:800561453acdecedaac137bf09cd719c7a440b6800ec182f077bb8e7025fb708"},
{file = "charset-normalizer-3.3.2.tar.gz", hash = "sha256:f30c3cb33b24454a82faecaf01b19c18562b1e89558fb6c56de4d9118a032fd5"},
{file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:25baf083bf6f6b341f4121c2f3c548875ee6f5339300e08be3f2b2ba1721cdd3"},
{file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:06435b539f889b1f6f4ac1758871aae42dc3a8c0e24ac9e60c2384973ad73027"},
{file = "charset_normalizer-3.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9063e24fdb1e498ab71cb7419e24622516c4a04476b17a2dab57e8baa30d6e03"},
{file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6897af51655e3691ff853668779c7bad41579facacf5fd7253b0133308cf000d"},
{file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1d3193f4a680c64b4b6a9115943538edb896edc190f0b222e73761716519268e"},
{file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cd70574b12bb8a4d2aaa0094515df2463cb429d8536cfb6c7ce983246983e5a6"},
{file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8465322196c8b4d7ab6d1e049e4c5cb460d0394da4a27d23cc242fbf0034b6b5"},
{file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a9a8e9031d613fd2009c182b69c7b2c1ef8239a0efb1df3f7c8da66d5dd3d537"},
{file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:beb58fe5cdb101e3a055192ac291b7a21e3b7ef4f67fa1d74e331a7f2124341c"},
{file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e06ed3eb3218bc64786f7db41917d4e686cc4856944f53d5bdf83a6884432e12"},
{file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:2e81c7b9c8979ce92ed306c249d46894776a909505d8f5a4ba55b14206e3222f"},
{file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:572c3763a264ba47b3cf708a44ce965d98555f618ca42c926a9c1616d8f34269"},
{file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fd1abc0d89e30cc4e02e4064dc67fcc51bd941eb395c502aac3ec19fab46b519"},
{file = "charset_normalizer-3.3.2-cp310-cp310-win32.whl", hash = "sha256:3d47fa203a7bd9c5b6cee4736ee84ca03b8ef23193c0d1ca99b5089f72645c73"},
{file = "charset_normalizer-3.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:10955842570876604d404661fbccbc9c7e684caf432c09c715ec38fbae45ae09"},
{file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:802fe99cca7457642125a8a88a084cef28ff0cf9407060f7b93dca5aa25480db"},
{file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:573f6eac48f4769d667c4442081b1794f52919e7edada77495aaed9236d13a96"},
{file = "charset_normalizer-3.3.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:549a3a73da901d5bc3ce8d24e0600d1fa85524c10287f6004fbab87672bf3e1e"},
{file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f27273b60488abe721a075bcca6d7f3964f9f6f067c8c4c605743023d7d3944f"},
{file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1ceae2f17a9c33cb48e3263960dc5fc8005351ee19db217e9b1bb15d28c02574"},
{file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:65f6f63034100ead094b8744b3b97965785388f308a64cf8d7c34f2f2e5be0c4"},
{file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:753f10e867343b4511128c6ed8c82f7bec3bd026875576dfd88483c5c73b2fd8"},
{file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4a78b2b446bd7c934f5dcedc588903fb2f5eec172f3d29e52a9096a43722adfc"},
{file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e537484df0d8f426ce2afb2d0f8e1c3d0b114b83f8850e5f2fbea0e797bd82ae"},
{file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:eb6904c354526e758fda7167b33005998fb68c46fbc10e013ca97f21ca5c8887"},
{file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:deb6be0ac38ece9ba87dea880e438f25ca3eddfac8b002a2ec3d9183a454e8ae"},
{file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4ab2fe47fae9e0f9dee8c04187ce5d09f48eabe611be8259444906793ab7cbce"},
{file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:80402cd6ee291dcb72644d6eac93785fe2c8b9cb30893c1af5b8fdd753b9d40f"},
{file = "charset_normalizer-3.3.2-cp311-cp311-win32.whl", hash = "sha256:7cd13a2e3ddeed6913a65e66e94b51d80a041145a026c27e6bb76c31a853c6ab"},
{file = "charset_normalizer-3.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:663946639d296df6a2bb2aa51b60a2454ca1cb29835324c640dafb5ff2131a77"},
{file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:0b2b64d2bb6d3fb9112bafa732def486049e63de9618b5843bcdd081d8144cd8"},
{file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:ddbb2551d7e0102e7252db79ba445cdab71b26640817ab1e3e3648dad515003b"},
{file = "charset_normalizer-3.3.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:55086ee1064215781fff39a1af09518bc9255b50d6333f2e4c74ca09fac6a8f6"},
{file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f4a014bc36d3c57402e2977dada34f9c12300af536839dc38c0beab8878f38a"},
{file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a10af20b82360ab00827f916a6058451b723b4e65030c5a18577c8b2de5b3389"},
{file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8d756e44e94489e49571086ef83b2bb8ce311e730092d2c34ca8f7d925cb20aa"},
{file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:90d558489962fd4918143277a773316e56c72da56ec7aa3dc3dbbe20fdfed15b"},
{file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ac7ffc7ad6d040517be39eb591cac5ff87416c2537df6ba3cba3bae290c0fed"},
{file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:7ed9e526742851e8d5cc9e6cf41427dfc6068d4f5a3bb03659444b4cabf6bc26"},
{file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8bdb58ff7ba23002a4c5808d608e4e6c687175724f54a5dade5fa8c67b604e4d"},
{file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:6b3251890fff30ee142c44144871185dbe13b11bab478a88887a639655be1068"},
{file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:b4a23f61ce87adf89be746c8a8974fe1c823c891d8f86eb218bb957c924bb143"},
{file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:efcb3f6676480691518c177e3b465bcddf57cea040302f9f4e6e191af91174d4"},
{file = "charset_normalizer-3.3.2-cp312-cp312-win32.whl", hash = "sha256:d965bba47ddeec8cd560687584e88cf699fd28f192ceb452d1d7ee807c5597b7"},
{file = "charset_normalizer-3.3.2-cp312-cp312-win_amd64.whl", hash = "sha256:96b02a3dc4381e5494fad39be677abcb5e6634bf7b4fa83a6dd3112607547001"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:95f2a5796329323b8f0512e09dbb7a1860c46a39da62ecb2324f116fa8fdc85c"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c002b4ffc0be611f0d9da932eb0f704fe2602a9a949d1f738e4c34c75b0863d5"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a981a536974bbc7a512cf44ed14938cf01030a99e9b3a06dd59578882f06f985"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3287761bc4ee9e33561a7e058c72ac0938c4f57fe49a09eae428fd88aafe7bb6"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42cb296636fcc8b0644486d15c12376cb9fa75443e00fb25de0b8602e64c1714"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0a55554a2fa0d408816b3b5cedf0045f4b8e1a6065aec45849de2d6f3f8e9786"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:c083af607d2515612056a31f0a8d9e0fcb5876b7bfc0abad3ecd275bc4ebc2d5"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:87d1351268731db79e0f8e745d92493ee2841c974128ef629dc518b937d9194c"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:bd8f7df7d12c2db9fab40bdd87a7c09b1530128315d047a086fa3ae3435cb3a8"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:c180f51afb394e165eafe4ac2936a14bee3eb10debc9d9e4db8958fe36afe711"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8c622a5fe39a48f78944a87d4fb8a53ee07344641b0562c540d840748571b811"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-win32.whl", hash = "sha256:db364eca23f876da6f9e16c9da0df51aa4f104a972735574842618b8c6d999d4"},
{file = "charset_normalizer-3.3.2-cp37-cp37m-win_amd64.whl", hash = "sha256:86216b5cee4b06df986d214f664305142d9c76df9b6512be2738aa72a2048f99"},
{file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:6463effa3186ea09411d50efc7d85360b38d5f09b870c48e4600f63af490e56a"},
{file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6c4caeef8fa63d06bd437cd4bdcf3ffefe6738fb1b25951440d80dc7df8c03ac"},
{file = "charset_normalizer-3.3.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:37e55c8e51c236f95b033f6fb391d7d7970ba5fe7ff453dad675e88cf303377a"},
{file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb69256e180cb6c8a894fee62b3afebae785babc1ee98b81cdf68bbca1987f33"},
{file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ae5f4161f18c61806f411a13b0310bea87f987c7d2ecdbdaad0e94eb2e404238"},
{file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b2b0a0c0517616b6869869f8c581d4eb2dd83a4d79e0ebcb7d373ef9956aeb0a"},
{file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:45485e01ff4d3630ec0d9617310448a8702f70e9c01906b0d0118bdf9d124cf2"},
{file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eb00ed941194665c332bf8e078baf037d6c35d7c4f3102ea2d4f16ca94a26dc8"},
{file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:2127566c664442652f024c837091890cb1942c30937add288223dc895793f898"},
{file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a50aebfa173e157099939b17f18600f72f84eed3049e743b68ad15bd69b6bf99"},
{file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:4d0d1650369165a14e14e1e47b372cfcb31d6ab44e6e33cb2d4e57265290044d"},
{file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:923c0c831b7cfcb071580d3f46c4baf50f174be571576556269530f4bbd79d04"},
{file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:06a81e93cd441c56a9b65d8e1d043daeb97a3d0856d177d5c90ba85acb3db087"},
{file = "charset_normalizer-3.3.2-cp38-cp38-win32.whl", hash = "sha256:6ef1d82a3af9d3eecdba2321dc1b3c238245d890843e040e41e470ffa64c3e25"},
{file = "charset_normalizer-3.3.2-cp38-cp38-win_amd64.whl", hash = "sha256:eb8821e09e916165e160797a6c17edda0679379a4be5c716c260e836e122f54b"},
{file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c235ebd9baae02f1b77bcea61bce332cb4331dc3617d254df3323aa01ab47bd4"},
{file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5b4c145409bef602a690e7cfad0a15a55c13320ff7a3ad7ca59c13bb8ba4d45d"},
{file = "charset_normalizer-3.3.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:68d1f8a9e9e37c1223b656399be5d6b448dea850bed7d0f87a8311f1ff3dabb0"},
{file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22afcb9f253dac0696b5a4be4a1c0f8762f8239e21b99680099abd9b2b1b2269"},
{file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e27ad930a842b4c5eb8ac0016b0a54f5aebbe679340c26101df33424142c143c"},
{file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1f79682fbe303db92bc2b1136016a38a42e835d932bab5b3b1bfcfbf0640e519"},
{file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b261ccdec7821281dade748d088bb6e9b69e6d15b30652b74cbbac25e280b796"},
{file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:122c7fa62b130ed55f8f285bfd56d5f4b4a5b503609d181f9ad85e55c89f4185"},
{file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d0eccceffcb53201b5bfebb52600a5fb483a20b61da9dbc885f8b103cbe7598c"},
{file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9f96df6923e21816da7e0ad3fd47dd8f94b2a5ce594e00677c0013018b813458"},
{file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:7f04c839ed0b6b98b1a7501a002144b76c18fb1c1850c8b98d458ac269e26ed2"},
{file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:34d1c8da1e78d2e001f363791c98a272bb734000fcef47a491c1e3b0505657a8"},
{file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ff8fa367d09b717b2a17a052544193ad76cd49979c805768879cb63d9ca50561"},
{file = "charset_normalizer-3.3.2-cp39-cp39-win32.whl", hash = "sha256:aed38f6e4fb3f5d6bf81bfa990a07806be9d83cf7bacef998ab1a9bd660a581f"},
{file = "charset_normalizer-3.3.2-cp39-cp39-win_amd64.whl", hash = "sha256:b01b88d45a6fcb69667cd6d2f7a9aeb4bf53760d7fc536bf679ec94fe9f3ff3d"},
{file = "charset_normalizer-3.3.2-py3-none-any.whl", hash = "sha256:3e4d1f6587322d2788836a99c69062fbb091331ec940e02d12d179c1d53e25fc"},
]
[[package]]
@@ -541,20 +541,20 @@ files = [
[[package]]
name = "filelock"
version = "3.12.4"
version = "3.13.1"
description = "A platform independent file lock."
category = "main"
optional = false
python-versions = ">=3.8"
files = [
{file = "filelock-3.12.4-py3-none-any.whl", hash = "sha256:08c21d87ded6e2b9da6728c3dff51baf1dcecf973b768ef35bcbc3447edb9ad4"},
{file = "filelock-3.12.4.tar.gz", hash = "sha256:2e6f249f1f3654291606e046b09f1fd5eac39b360664c27f5aad072012f8bcbd"},
{file = "filelock-3.13.1-py3-none-any.whl", hash = "sha256:57dbda9b35157b05fb3e58ee91448612eb674172fab98ee235ccb0b5bee19a1c"},
{file = "filelock-3.13.1.tar.gz", hash = "sha256:521f5f56c50f8426f5e03ad3b281b490a87ef15bc6c526f168290f0c7148d44e"},
]
[package.extras]
docs = ["furo (>=2023.7.26)", "sphinx (>=7.1.2)", "sphinx-autodoc-typehints (>=1.24)"]
testing = ["covdefaults (>=2.3)", "coverage (>=7.3)", "diff-cover (>=7.7)", "pytest (>=7.4)", "pytest-cov (>=4.1)", "pytest-mock (>=3.11.1)", "pytest-timeout (>=2.1)"]
typing = ["typing-extensions (>=4.7.1)"]
docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.24)"]
testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"]
typing = ["typing-extensions (>=4.8)"]
[[package]]
name = "frozenlist"
@@ -837,14 +837,14 @@ files = [
[[package]]
name = "langchain"
version = "0.0.324"
version = "0.0.330"
description = "Building applications with LLMs through composability"
category = "main"
optional = false
python-versions = ">=3.8.1,<4.0"
files = [
{file = "langchain-0.0.324-py3-none-any.whl", hash = "sha256:9be84d14e264567d52b93d0d2ba1e8cbf38c6e50a3914be02dbd9ea0fabaafd9"},
{file = "langchain-0.0.324.tar.gz", hash = "sha256:d8dc589aa57699d51eeef8ce0507cd3faac4465ad0ff08dfb0a19e5661c3af44"},
{file = "langchain-0.0.330-py3-none-any.whl", hash = "sha256:ed557f4d680e02d9a05b175cae1ba146b7239d4d429d1d5271d4578b4956dbd6"},
{file = "langchain-0.0.330.tar.gz", hash = "sha256:5bed52769b63d76eb63589193e2efb66f5c7c429726af608e658f635335bd46a"},
]
[package.dependencies]
@@ -862,14 +862,14 @@ SQLAlchemy = ">=1.4,<3"
tenacity = ">=8.1.0,<9.0.0"
[package.extras]
all = ["O365 (>=2.0.26,<3.0.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "amadeus (>=8.1.0)", "arxiv (>=1.4,<2.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "awadb (>=0.3.9,<0.4.0)", "azure-ai-formrecognizer (>=3.2.1,<4.0.0)", "azure-ai-vision (>=0.11.1b1,<0.12.0)", "azure-cognitiveservices-speech (>=1.28.0,<2.0.0)", "azure-cosmos (>=4.4.0b1,<5.0.0)", "azure-identity (>=1.12.0,<2.0.0)", "beautifulsoup4 (>=4,<5)", "clarifai (>=9.1.0)", "clickhouse-connect (>=0.5.14,<0.6.0)", "cohere (>=4,<5)", "deeplake (>=3.6.8,<4.0.0)", "docarray[hnswlib] (>=0.32.0,<0.33.0)", "duckduckgo-search (>=3.8.3,<4.0.0)", "elasticsearch (>=8,<9)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "google-api-python-client (==2.70.0)", "google-auth (>=2.18.1,<3.0.0)", "google-search-results (>=2,<3)", "gptcache (>=0.1.7)", "html2text (>=2020.1.16,<2021.0.0)", "huggingface_hub (>=0,<1)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "lancedb (>=0.1,<0.2)", "langkit (>=0.0.6,<0.1.0)", "lark (>=1.1.5,<2.0.0)", "libdeeplake (>=0.0.60,<0.0.61)", "librosa (>=0.10.0.post2,<0.11.0)", "lxml (>=4.9.2,<5.0.0)", "manifest-ml (>=0.0.1,<0.0.2)", "marqo (>=1.2.4,<2.0.0)", "momento (>=1.10.1,<2.0.0)", "nebula3-python (>=3.4.0,<4.0.0)", "neo4j (>=5.8.1,<6.0.0)", "networkx (>=2.6.3,<4)", "nlpcloud (>=1,<2)", "nltk (>=3,<4)", "nomic (>=1.0.43,<2.0.0)", "openai (>=0,<1)", "openlm (>=0.0.5,<0.0.6)", "opensearch-py (>=2.0.0,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pexpect (>=4.8.0,<5.0.0)", "pgvector (>=0.1.6,<0.2.0)", "pinecone-client (>=2,<3)", "pinecone-text (>=0.4.2,<0.5.0)", "psycopg2-binary (>=2.9.5,<3.0.0)", "pymongo (>=4.3.3,<5.0.0)", "pyowm (>=3.3.0,<4.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pytesseract (>=0.3.10,<0.4.0)", "python-arango (>=7.5.9,<8.0.0)", "pyvespa (>=0.33.0,<0.34.0)", "qdrant-client (>=1.3.1,<2.0.0)", "rdflib (>=6.3.2,<7.0.0)", "redis (>=4,<5)", "requests-toolbelt (>=1.0.0,<2.0.0)", "sentence-transformers (>=2,<3)", "singlestoredb (>=0.7.1,<0.8.0)", "tensorflow-text (>=2.11.0,<3.0.0)", "tigrisdb (>=1.0.0b6,<2.0.0)", "tiktoken (>=0.3.2,<0.6.0)", "torch (>=1,<3)", "transformers (>=4,<5)", "weaviate-client (>=3,<4)", "wikipedia (>=1,<2)", "wolframalpha (==5.0.0)"]
all = ["O365 (>=2.0.26,<3.0.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "amadeus (>=8.1.0)", "arxiv (>=1.4,<2.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "awadb (>=0.3.9,<0.4.0)", "azure-ai-formrecognizer (>=3.2.1,<4.0.0)", "azure-ai-vision (>=0.11.1b1,<0.12.0)", "azure-cognitiveservices-speech (>=1.28.0,<2.0.0)", "azure-cosmos (>=4.4.0b1,<5.0.0)", "azure-identity (>=1.12.0,<2.0.0)", "beautifulsoup4 (>=4,<5)", "clarifai (>=9.1.0)", "clickhouse-connect (>=0.5.14,<0.6.0)", "cohere (>=4,<5)", "deeplake (>=3.8.3,<4.0.0)", "docarray[hnswlib] (>=0.32.0,<0.33.0)", "duckduckgo-search (>=3.8.3,<4.0.0)", "elasticsearch (>=8,<9)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "google-api-python-client (==2.70.0)", "google-auth (>=2.18.1,<3.0.0)", "google-search-results (>=2,<3)", "gptcache (>=0.1.7)", "html2text (>=2020.1.16,<2021.0.0)", "huggingface_hub (>=0,<1)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "lancedb (>=0.1,<0.2)", "langkit (>=0.0.6,<0.1.0)", "lark (>=1.1.5,<2.0.0)", "librosa (>=0.10.0.post2,<0.11.0)", "lxml (>=4.9.2,<5.0.0)", "manifest-ml (>=0.0.1,<0.0.2)", "marqo (>=1.2.4,<2.0.0)", "momento (>=1.10.1,<2.0.0)", "nebula3-python (>=3.4.0,<4.0.0)", "neo4j (>=5.8.1,<6.0.0)", "networkx (>=2.6.3,<4)", "nlpcloud (>=1,<2)", "nltk (>=3,<4)", "nomic (>=1.0.43,<2.0.0)", "openai (>=0,<1)", "openlm (>=0.0.5,<0.0.6)", "opensearch-py (>=2.0.0,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pexpect (>=4.8.0,<5.0.0)", "pgvector (>=0.1.6,<0.2.0)", "pinecone-client (>=2,<3)", "pinecone-text (>=0.4.2,<0.5.0)", "psycopg2-binary (>=2.9.5,<3.0.0)", "pymongo (>=4.3.3,<5.0.0)", "pyowm (>=3.3.0,<4.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pytesseract (>=0.3.10,<0.4.0)", "python-arango (>=7.5.9,<8.0.0)", "pyvespa (>=0.33.0,<0.34.0)", "qdrant-client (>=1.3.1,<2.0.0)", "rdflib (>=6.3.2,<7.0.0)", "redis (>=4,<5)", "requests-toolbelt (>=1.0.0,<2.0.0)", "sentence-transformers (>=2,<3)", "singlestoredb (>=0.7.1,<0.8.0)", "tensorflow-text (>=2.11.0,<3.0.0)", "tigrisdb (>=1.0.0b6,<2.0.0)", "tiktoken (>=0.3.2,<0.6.0)", "torch (>=1,<3)", "transformers (>=4,<5)", "weaviate-client (>=3,<4)", "wikipedia (>=1,<2)", "wolframalpha (==5.0.0)"]
azure = ["azure-ai-formrecognizer (>=3.2.1,<4.0.0)", "azure-ai-vision (>=0.11.1b1,<0.12.0)", "azure-cognitiveservices-speech (>=1.28.0,<2.0.0)", "azure-core (>=1.26.4,<2.0.0)", "azure-cosmos (>=4.4.0b1,<5.0.0)", "azure-identity (>=1.12.0,<2.0.0)", "azure-search-documents (==11.4.0b8)", "openai (>=0,<1)"]
clarifai = ["clarifai (>=9.1.0)"]
cli = ["typer (>=0.9.0,<0.10.0)"]
cohere = ["cohere (>=4,<5)"]
docarray = ["docarray[hnswlib] (>=0.32.0,<0.33.0)"]
embeddings = ["sentence-transformers (>=2,<3)"]
extended-testing = ["aiosqlite (>=0.19.0,<0.20.0)", "amazon-textract-caller (<2)", "anthropic (>=0.3.11,<0.4.0)", "arxiv (>=1.4,<2.0)", "assemblyai (>=0.17.0,<0.18.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "beautifulsoup4 (>=4,<5)", "bibtexparser (>=1.4.0,<2.0.0)", "cassio (>=0.1.0,<0.2.0)", "chardet (>=5.1.0,<6.0.0)", "dashvector (>=1.0.1,<2.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "google-cloud-documentai (>=2.20.1,<3.0.0)", "gql (>=3.4.1,<4.0.0)", "html2text (>=2020.1.16,<2021.0.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "motor (>=3.3.1,<4.0.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "numexpr (>=2.8.6,<3.0.0)", "openai (>=0,<1)", "openapi-pydantic (>=0.3.2,<0.4.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "psychicapi (>=0.8.0,<0.9.0)", "py-trello (>=0.19.0,<0.20.0)", "pymupdf (>=1.22.3,<2.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pypdfium2 (>=4.10.0,<5.0.0)", "pyspark (>=3.4.0,<4.0.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "rapidfuzz (>=3.1.1,<4.0.0)", "rapidocr-onnxruntime (>=1.3.2,<2.0.0)", "requests-toolbelt (>=1.0.0,<2.0.0)", "rspace_client (>=2.5.0,<3.0.0)", "scikit-learn (>=1.2.2,<2.0.0)", "sqlite-vss (>=0.1.2,<0.2.0)", "streamlit (>=1.18.0,<2.0.0)", "sympy (>=1.12,<2.0)", "telethon (>=1.28.5,<2.0.0)", "timescale-vector (>=0.0.1,<0.0.2)", "tqdm (>=4.48.0)", "upstash-redis (>=0.15.0,<0.16.0)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)"]
extended-testing = ["aiosqlite (>=0.19.0,<0.20.0)", "aleph-alpha-client (>=2.15.0,<3.0.0)", "anthropic (>=0.3.11,<0.4.0)", "arxiv (>=1.4,<2.0)", "assemblyai (>=0.17.0,<0.18.0)", "atlassian-python-api (>=3.36.0,<4.0.0)", "beautifulsoup4 (>=4,<5)", "bibtexparser (>=1.4.0,<2.0.0)", "cassio (>=0.1.0,<0.2.0)", "chardet (>=5.1.0,<6.0.0)", "dashvector (>=1.0.1,<2.0.0)", "esprima (>=4.0.1,<5.0.0)", "faiss-cpu (>=1,<2)", "feedparser (>=6.0.10,<7.0.0)", "fireworks-ai (>=0.6.0,<0.7.0)", "geopandas (>=0.13.1,<0.14.0)", "gitpython (>=3.1.32,<4.0.0)", "google-cloud-documentai (>=2.20.1,<3.0.0)", "gql (>=3.4.1,<4.0.0)", "html2text (>=2020.1.16,<2021.0.0)", "jinja2 (>=3,<4)", "jq (>=1.4.1,<2.0.0)", "jsonschema (>1)", "lxml (>=4.9.2,<5.0.0)", "markdownify (>=0.11.6,<0.12.0)", "motor (>=3.3.1,<4.0.0)", "mwparserfromhell (>=0.6.4,<0.7.0)", "mwxml (>=0.3.3,<0.4.0)", "newspaper3k (>=0.2.8,<0.3.0)", "numexpr (>=2.8.6,<3.0.0)", "openai (>=0,<1)", "openapi-pydantic (>=0.3.2,<0.4.0)", "pandas (>=2.0.1,<3.0.0)", "pdfminer-six (>=20221105,<20221106)", "pgvector (>=0.1.6,<0.2.0)", "psychicapi (>=0.8.0,<0.9.0)", "py-trello (>=0.19.0,<0.20.0)", "pymupdf (>=1.22.3,<2.0.0)", "pypdf (>=3.4.0,<4.0.0)", "pypdfium2 (>=4.10.0,<5.0.0)", "pyspark (>=3.4.0,<4.0.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "rapidfuzz (>=3.1.1,<4.0.0)", "rapidocr-onnxruntime (>=1.3.2,<2.0.0)", "requests-toolbelt (>=1.0.0,<2.0.0)", "rspace_client (>=2.5.0,<3.0.0)", "scikit-learn (>=1.2.2,<2.0.0)", "sqlite-vss (>=0.1.2,<0.2.0)", "streamlit (>=1.18.0,<2.0.0)", "sympy (>=1.12,<2.0)", "telethon (>=1.28.5,<2.0.0)", "timescale-vector (>=0.0.1,<0.0.2)", "tqdm (>=4.48.0)", "upstash-redis (>=0.15.0,<0.16.0)", "xata (>=1.0.0a7,<2.0.0)", "xmltodict (>=0.13.0,<0.14.0)"]
javascript = ["esprima (>=4.0.1,<5.0.0)"]
llms = ["clarifai (>=9.1.0)", "cohere (>=4,<5)", "huggingface_hub (>=0,<1)", "manifest-ml (>=0.0.1,<0.0.2)", "nlpcloud (>=1,<2)", "openai (>=0,<1)", "openlm (>=0.0.5,<0.0.6)", "torch (>=1,<3)", "transformers (>=4,<5)"]
openai = ["openai (>=0,<1)", "tiktoken (>=0.3.2,<0.6.0)"]
@@ -878,14 +878,14 @@ text-helpers = ["chardet (>=5.1.0,<6.0.0)"]
[[package]]
name = "langsmith"
version = "0.0.52"
version = "0.0.56"
description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
category = "main"
optional = false
python-versions = ">=3.8.1,<4.0"
files = [
{file = "langsmith-0.0.52-py3-none-any.whl", hash = "sha256:d02a0ade5a53b36143084e57003ed38ccbdf5fc15a5a0eb14f8989ceaee0b807"},
{file = "langsmith-0.0.52.tar.gz", hash = "sha256:1dc29082d257deea1859cb22c53d9481ca5c4a37f3af40c0f9d300fb8adc91db"},
{file = "langsmith-0.0.56-py3-none-any.whl", hash = "sha256:5aed1ad2395700442a6511651eca17d60eff56878f18bdd9e1d20b3c6f7e016c"},
{file = "langsmith-0.0.56.tar.gz", hash = "sha256:98382931f61a984a3d02cad07e4b986a0a7c843f87830172692c987deb8ba554"},
]
[package.dependencies]
@@ -894,14 +894,14 @@ requests = ">=2,<3"
[[package]]
name = "llama-index"
version = "0.8.53.post3"
version = "0.8.59"
description = "Interface between LLMs and your data"
category = "main"
optional = false
python-versions = ">=3.8.1,<3.12"
files = [
{file = "llama_index-0.8.53.post3-py3-none-any.whl", hash = "sha256:9333a32a4a394212c27e7e76a1eee0fd3d944c9be86250545953ad4fbd7f0d49"},
{file = "llama_index-0.8.53.post3.tar.gz", hash = "sha256:2cc1b30350bd8292377841153415190a36e3bc50ccd46bb7908b420202b39770"},
{file = "llama_index-0.8.59-py3-none-any.whl", hash = "sha256:3627190cb0b84934b5662116b0b764e854f677a5d1a42ef35aecb0f9f226170c"},
{file = "llama_index-0.8.59.tar.gz", hash = "sha256:428b793186ecf9f42bdcf2f58944926c0278d4baa07ae5066a309a36127beca8"},
]
[package.dependencies]
@@ -925,7 +925,7 @@ urllib3 = "<2"
[package.extras]
local-models = ["optimum[onnxruntime] (>=1.13.2,<2.0.0)", "sentencepiece (>=0.1.99,<0.2.0)", "transformers[torch] (>=4.34.0,<5.0.0)"]
postgres = ["asyncpg (>=0.28.0,<0.29.0)", "pgvector (>=0.1.0,<0.2.0)", "psycopg-binary (>=3.1.12,<4.0.0)"]
query-tools = ["guidance (>=0.0.64,<0.0.65)", "jsonpath-ng (>=1.6.0,<2.0.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "scikit-learn (<1.3.0)", "spacy (>=3.7.1,<4.0.0)"]
query-tools = ["guidance (>=0.0.64,<0.0.65)", "jsonpath-ng (>=1.6.0,<2.0.0)", "lm-format-enforcer (>=0.4.3,<0.5.0)", "rank-bm25 (>=0.2.2,<0.3.0)", "scikit-learn (<1.3.0)", "spacy (>=3.7.1,<4.0.0)"]
[[package]]
name = "markdown-it-py"
@@ -1305,6 +1305,20 @@ files = [
{file = "pathspec-0.11.2.tar.gz", hash = "sha256:e0d8d0ac2f12da61956eb2306b69f9469b42f4deb0f3cb6ed47b9cce9996ced3"},
]
[[package]]
name = "pgvector"
version = "0.2.3"
description = "pgvector support for Python"
category = "main"
optional = false
python-versions = ">=3.8"
files = [
{file = "pgvector-0.2.3-py2.py3-none-any.whl", hash = "sha256:9d53dc01138ecc7c9aca64e4680cfa9edf4c38f9cb8ed7098317871fdd211824"},
]
[package.dependencies]
numpy = "*"
[[package]]
name = "platformdirs"
version = "3.11.0"
@@ -1370,43 +1384,231 @@ files = [
[package.dependencies]
wcwidth = "*"
[[package]]
name = "psycopg"
version = "3.1.12"
description = "PostgreSQL database adapter for Python"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "psycopg-3.1.12-py3-none-any.whl", hash = "sha256:8ec5230d6a7eb654b4fb3cf2d3eda8871d68f24807b934790504467f1deee9f8"},
{file = "psycopg-3.1.12.tar.gz", hash = "sha256:cec7ad2bc6a8510e56c45746c631cf9394148bdc8a9a11fd8cf8554ce129ae78"},
]
[package.dependencies]
typing-extensions = ">=4.1"
tzdata = {version = "*", markers = "sys_platform == \"win32\""}
[package.extras]
binary = ["psycopg-binary (==3.1.12)"]
c = ["psycopg-c (==3.1.12)"]
dev = ["black (>=23.1.0)", "dnspython (>=2.1)", "flake8 (>=4.0)", "mypy (>=1.4.1)", "types-setuptools (>=57.4)", "wheel (>=0.37)"]
docs = ["Sphinx (>=5.0)", "furo (==2022.6.21)", "sphinx-autobuild (>=2021.3.14)", "sphinx-autodoc-typehints (>=1.12)"]
pool = ["psycopg-pool"]
test = ["anyio (>=3.6.2,<4.0)", "mypy (>=1.4.1)", "pproxy (>=2.7)", "pytest (>=6.2.5)", "pytest-cov (>=3.0)", "pytest-randomly (>=3.5)"]
[[package]]
name = "psycopg-binary"
version = "3.1.12"
description = "PostgreSQL database adapter for Python -- C optimisation distribution"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "psycopg_binary-3.1.12-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:29a69f62aae8617361376d9ed1e34966ae9c3a74c4ab3aa430a7ce0c11530862"},
{file = "psycopg_binary-3.1.12-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:7308316fdb6796399041b80db0ab9f356504ed26427e46834ade82ba94b067ce"},
{file = "psycopg_binary-3.1.12-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:130752b9b2f8d071f179e257b9698cedfe4546be81ad5ecd8ed52cf9d725580d"},
{file = "psycopg_binary-3.1.12-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:45bcecc96a6e6fe11e06b75f7ba8005d6f717f16fae7ab1cf5a0aec5191f87c3"},
{file = "psycopg_binary-3.1.12-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bc3f0fcc4fcccffda2450c725bee9fad73bc6c110cfbe3b8a777063845d9c6b9"},
{file = "psycopg_binary-3.1.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f93749f0fe69cfbfec22af690bb4b241f1a4347c57be26fe2e5b70588f7d602f"},
{file = "psycopg_binary-3.1.12-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:36147f708cc6a9d74c2b8d880f8dd3a6d53364b5c487536adaa022d435c90733"},
{file = "psycopg_binary-3.1.12-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:2bbcc6fbabc2b92d18d955d9fa104fd9d8bd2dcb97a279c4e788c6b714ffd1af"},
{file = "psycopg_binary-3.1.12-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:0dee8a1ecc501d9c3db06d08184712459bbb5806a09121c3a25e8cbe91e234d7"},
{file = "psycopg_binary-3.1.12-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:49d6acf228edb5bd9000735b89b780b18face776d081b905cf68e149d57dfcc1"},
{file = "psycopg_binary-3.1.12-cp310-cp310-win_amd64.whl", hash = "sha256:ee65335781a54f29f4abc28060a6188c41bdd42fdc3cbc1dd84695ed8ef18321"},
{file = "psycopg_binary-3.1.12-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d401722aa38bda64d1ba8293f6dad99f6f684711e2c016a93f138f2bbcff2a4b"},
{file = "psycopg_binary-3.1.12-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:46eac158e8e794d9414a8fe7706beeee9b1ecc4accbea914314825ace8137105"},
{file = "psycopg_binary-3.1.12-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3f017400679aa38f6cb22b888b8ec198a5b100ec2132e6b3bcfa797b14b5b438"},
{file = "psycopg_binary-3.1.12-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d176c4614f5208ab9938d5426d61627c8fbc7f8dab53fef42c8bf2ab8605aa51"},
{file = "psycopg_binary-3.1.12-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c48c4f3fcfd9e75e3fdb18eea320de591e06059a859280ec26ce8d753299353d"},
{file = "psycopg_binary-3.1.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:98fce28d8136bdd883f20d26467bf259b5fb559eb64d8f83695690714cdfdad3"},
{file = "psycopg_binary-3.1.12-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e4a0f44bc29fc1b56ee1c865796cbe354078ee1e985f898e4915db185055bf7d"},
{file = "psycopg_binary-3.1.12-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:6def4f238ca02d6b42336b405d02729c081c978cda9b6ba7549a9c63a91ba823"},
{file = "psycopg_binary-3.1.12-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:000838cb5ab7851116b462e58893a96b0f1e35864135a6283f3242a730ec45d3"},
{file = "psycopg_binary-3.1.12-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7949e1aefe339f04dbecac6aa036c9cd137a58f966c4b96ab933823c340ee12"},
{file = "psycopg_binary-3.1.12-cp311-cp311-win_amd64.whl", hash = "sha256:b32922872460575083487de41e17e8cf308c3550da02c704efe42960bc6c19de"},
{file = "psycopg_binary-3.1.12-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:70054ada2f890d004dc3d5ff908e34aecb085fd599d40db2975c09a39c50dfc3"},
{file = "psycopg_binary-3.1.12-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:7544d6d74f5b5f9daafe8a4ed7d266787d62a2bf16f5120c45d42d1f4a856bc8"},
{file = "psycopg_binary-3.1.12-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:43197161099cb4e36a9ca44c10657908b619d7263ffcff30932ad4627430dc3c"},
{file = "psycopg_binary-3.1.12-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:68398cdf3aedd4042b1126b9aba34615f1ab592831483282f19f0159fce5ca75"},
{file = "psycopg_binary-3.1.12-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:77ae6cda3ffee2425aca9ea7af57296d0c701e2ac5897b48b95dfee050234592"},
{file = "psycopg_binary-3.1.12-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:278e8888e90fb6ebd7eae8ccb85199eafd712b734e641e0d40f2a903e946102d"},
{file = "psycopg_binary-3.1.12-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:047c4ba8d3089465b0a69c4c669128df43403867858d78da6b40b33788bfa89f"},
{file = "psycopg_binary-3.1.12-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8248b11ac490bb74de80457ab0e9cef31c08164ff7b867031927a17e5c9e19ed"},
{file = "psycopg_binary-3.1.12-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:6979c02acb9783c6134ee516751b8f891a2d4db7f73ebecc9e92750283d6fb99"},
{file = "psycopg_binary-3.1.12-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:eaf2375b724ad61ee82a5c2a849e57b12b3cb510ec8845084132bbb907cb3335"},
{file = "psycopg_binary-3.1.12-cp312-cp312-win_amd64.whl", hash = "sha256:6177cfa6f872a9cc84dbfc7dc163af6ef01639c50acc9a441673f29c2305c37a"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b81427fd5a97c9b4ac12f3b8d985870b0c3866b5fc2e72e51cacd3630ffd6466"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3f17a2c393879aa54f840540009d0e70a30d22ffa0038d81e258ac2c99b15d74"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6c6a5d125a61101ef5ab7384206e43952fe2a5fca997b96d28a28a752512f900"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:942a18df448a33d77aa7dff7e93062ace7926608a965db003622cb5f27910ba2"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3195baff3e3e5d71828400d38af0ffc5a15d7dca2bfaadc9eb615235774b9290"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:f26bb34e0e9bb83fba00c4835f91f5c5348cdf689df8c8b503571c0d0027c8f5"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:104bdc85c5c4884b3f900155b635588a28740f561b32a3e27c38bcd249feba41"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:53464cb71e06faac479f44b8870f115004187e1dfb299b9725d1d7f85d9e5479"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:052835aac03ee6a9d5b6fe35c468da79084ebe38709e6d3c24ff5b9422fb2947"},
{file = "psycopg_binary-3.1.12-cp37-cp37m-win_amd64.whl", hash = "sha256:a21a7fffec1a225b26d72adb960d771fc5a9aba8e1f7dd710abcaa9a980e9740"},
{file = "psycopg_binary-3.1.12-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6925a543e88cdfd1a2f679c7a33c08f107de60728a4a3c52f88d4491d40a7f51"},
{file = "psycopg_binary-3.1.12-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b04957bd5caff94eac38306357b6d448dd20a6f68fd998e115e3731a55118d83"},
{file = "psycopg_binary-3.1.12-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f6f55979804853efa5ce84d7ef59ff3772e0823247497f7d4a6870e6527fd791"},
{file = "psycopg_binary-3.1.12-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7d343e1f564fdc8964e1c08b8a6c1f6ebf4b45ee5631b5241c9cbac793f4500c"},
{file = "psycopg_binary-3.1.12-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:48c4ba35f717783327931aa9da6e6aab81b6b90f3e6b902b18e269d73e7d0882"},
{file = "psycopg_binary-3.1.12-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d77c95d6086e0714225764772bf8110bb29dfbc6c32aa56e725a01998ce20e7c"},
{file = "psycopg_binary-3.1.12-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6dea80e65c7a97150d555b64744e7279ff4c6b259d27580b756a5b282a7d44e3"},
{file = "psycopg_binary-3.1.12-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:03a851123d0155e1d6ca5b6cccf624e2fc71c8f7eae76f5100196e0fca047d30"},
{file = "psycopg_binary-3.1.12-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:99ad07b9ef5853713bb63c55e179af52994e96f445c5d66b87d8b986182922ef"},
{file = "psycopg_binary-3.1.12-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:4441d0f8ecae499a6ac5c79078c9fcd406c0bf70e72cb6cba888aca51aa46943"},
{file = "psycopg_binary-3.1.12-cp38-cp38-win_amd64.whl", hash = "sha256:cb45a709b966583773acc3418fffbf6d73b014943b6efceca6a7d3ca960956cf"},
{file = "psycopg_binary-3.1.12-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5112245daf98e22046316e72690689a8952a9b078908206a6b16cd28d84cde7c"},
{file = "psycopg_binary-3.1.12-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c2eb94bf0bd653c940517cd92dc4f98c85d505f69013b247dda747413bcf0a8b"},
{file = "psycopg_binary-3.1.12-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d41b03ce52a109858735ac19fe0295e3f77bef0388d6a3e105074ad68f4a9645"},
{file = "psycopg_binary-3.1.12-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4fddc3c9beaf745de3da10230f0144a4c667b21c3f7a94a3bb1fb004954c9810"},
{file = "psycopg_binary-3.1.12-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c5987616698c895ae079fb5e26811b72948cb3b75c2c690446379298e96c1568"},
{file = "psycopg_binary-3.1.12-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f4ae45d58bd79795a2d23d05be5496b226b09ac2688b9ed9808e13c345e2d542"},
{file = "psycopg_binary-3.1.12-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:bb98252ac8ba41a121f88979e4232ffc1d6722c953531cbdae2b328322308581"},
{file = "psycopg_binary-3.1.12-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:ca09e4937c9db24a58951ee9aea7aae7bca11a954b30c59f3b271e9bdebd80d7"},
{file = "psycopg_binary-3.1.12-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:03e321e149d051daa20892ed1bb3beabf0aae98a8c37da30ec80fa12306f9ba9"},
{file = "psycopg_binary-3.1.12-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d819cb43cccc10ba501b9d462409fcaaeb19f77b8379b2e7ca0ced4a49446d4a"},
{file = "psycopg_binary-3.1.12-cp39-cp39-win_amd64.whl", hash = "sha256:c9eb2ba27760bc1303f0708ba95b9e4f3f3b77a081ef4f7f53375c71da3a1bee"},
]
[[package]]
name = "psycopg2-binary"
version = "2.9.9"
description = "psycopg2 - Python-PostgreSQL Database Adapter"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "psycopg2-binary-2.9.9.tar.gz", hash = "sha256:7f01846810177d829c7692f1f5ada8096762d9172af1b1a28d4ab5b77c923c1c"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c2470da5418b76232f02a2fcd2229537bb2d5a7096674ce61859c3229f2eb202"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c6af2a6d4b7ee9615cbb162b0738f6e1fd1f5c3eda7e5da17861eacf4c717ea7"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:75723c3c0fbbf34350b46a3199eb50638ab22a0228f93fb472ef4d9becc2382b"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:83791a65b51ad6ee6cf0845634859d69a038ea9b03d7b26e703f94c7e93dbcf9"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0ef4854e82c09e84cc63084a9e4ccd6d9b154f1dbdd283efb92ecd0b5e2b8c84"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ed1184ab8f113e8d660ce49a56390ca181f2981066acc27cf637d5c1e10ce46e"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d2997c458c690ec2bc6b0b7ecbafd02b029b7b4283078d3b32a852a7ce3ddd98"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:b58b4710c7f4161b5e9dcbe73bb7c62d65670a87df7bcce9e1faaad43e715245"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:0c009475ee389757e6e34611d75f6e4f05f0cf5ebb76c6037508318e1a1e0d7e"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8dbf6d1bc73f1d04ec1734bae3b4fb0ee3cb2a493d35ede9badbeb901fb40f6f"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-win32.whl", hash = "sha256:3f78fd71c4f43a13d342be74ebbc0666fe1f555b8837eb113cb7416856c79682"},
{file = "psycopg2_binary-2.9.9-cp310-cp310-win_amd64.whl", hash = "sha256:876801744b0dee379e4e3c38b76fc89f88834bb15bf92ee07d94acd06ec890a0"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ee825e70b1a209475622f7f7b776785bd68f34af6e7a46e2e42f27b659b5bc26"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1ea665f8ce695bcc37a90ee52de7a7980be5161375d42a0b6c6abedbf0d81f0f"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:143072318f793f53819048fdfe30c321890af0c3ec7cb1dfc9cc87aa88241de2"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c332c8d69fb64979ebf76613c66b985414927a40f8defa16cf1bc028b7b0a7b0"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f7fc5a5acafb7d6ccca13bfa8c90f8c51f13d8fb87d95656d3950f0158d3ce53"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:977646e05232579d2e7b9c59e21dbe5261f403a88417f6a6512e70d3f8a046be"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:b6356793b84728d9d50ead16ab43c187673831e9d4019013f1402c41b1db9b27"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:bc7bb56d04601d443f24094e9e31ae6deec9ccb23581f75343feebaf30423359"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:77853062a2c45be16fd6b8d6de2a99278ee1d985a7bd8b103e97e41c034006d2"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:78151aa3ec21dccd5cdef6c74c3e73386dcdfaf19bced944169697d7ac7482fc"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-win32.whl", hash = "sha256:dc4926288b2a3e9fd7b50dc6a1909a13bbdadfc67d93f3374d984e56f885579d"},
{file = "psycopg2_binary-2.9.9-cp311-cp311-win_amd64.whl", hash = "sha256:b76bedd166805480ab069612119ea636f5ab8f8771e640ae103e05a4aae3e417"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:8532fd6e6e2dc57bcb3bc90b079c60de896d2128c5d9d6f24a63875a95a088cf"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b0605eaed3eb239e87df0d5e3c6489daae3f7388d455d0c0b4df899519c6a38d"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f8544b092a29a6ddd72f3556a9fcf249ec412e10ad28be6a0c0d948924f2212"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2d423c8d8a3c82d08fe8af900ad5b613ce3632a1249fd6a223941d0735fce493"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2e5afae772c00980525f6d6ecf7cbca55676296b580c0e6abb407f15f3706996"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6e6f98446430fdf41bd36d4faa6cb409f5140c1c2cf58ce0bbdaf16af7d3f119"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:c77e3d1862452565875eb31bdb45ac62502feabbd53429fdc39a1cc341d681ba"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:cb16c65dcb648d0a43a2521f2f0a2300f40639f6f8c1ecbc662141e4e3e1ee07"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:911dda9c487075abd54e644ccdf5e5c16773470a6a5d3826fda76699410066fb"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:57fede879f08d23c85140a360c6a77709113efd1c993923c59fde17aa27599fe"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-win32.whl", hash = "sha256:64cf30263844fa208851ebb13b0732ce674d8ec6a0c86a4e160495d299ba3c93"},
{file = "psycopg2_binary-2.9.9-cp312-cp312-win_amd64.whl", hash = "sha256:81ff62668af011f9a48787564ab7eded4e9fb17a4a6a74af5ffa6a457400d2ab"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:2293b001e319ab0d869d660a704942c9e2cce19745262a8aba2115ef41a0a42a"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:03ef7df18daf2c4c07e2695e8cfd5ee7f748a1d54d802330985a78d2a5a6dca9"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0a602ea5aff39bb9fac6308e9c9d82b9a35c2bf288e184a816002c9fae930b77"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8359bf4791968c5a78c56103702000105501adb557f3cf772b2c207284273984"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:275ff571376626195ab95a746e6a04c7df8ea34638b99fc11160de91f2fef503"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:f9b5571d33660d5009a8b3c25dc1db560206e2d2f89d3df1cb32d72c0d117d52"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:420f9bbf47a02616e8554e825208cb947969451978dceb77f95ad09c37791dae"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:4154ad09dac630a0f13f37b583eae260c6aa885d67dfbccb5b02c33f31a6d420"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:a148c5d507bb9b4f2030a2025c545fccb0e1ef317393eaba42e7eabd28eb6041"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-win32.whl", hash = "sha256:68fc1f1ba168724771e38bee37d940d2865cb0f562380a1fb1ffb428b75cb692"},
{file = "psycopg2_binary-2.9.9-cp37-cp37m-win_amd64.whl", hash = "sha256:281309265596e388ef483250db3640e5f414168c5a67e9c665cafce9492eda2f"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:60989127da422b74a04345096c10d416c2b41bd7bf2a380eb541059e4e999980"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:246b123cc54bb5361588acc54218c8c9fb73068bf227a4a531d8ed56fa3ca7d6"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:34eccd14566f8fe14b2b95bb13b11572f7c7d5c36da61caf414d23b91fcc5d94"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:18d0ef97766055fec15b5de2c06dd8e7654705ce3e5e5eed3b6651a1d2a9a152"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d3f82c171b4ccd83bbaf35aa05e44e690113bd4f3b7b6cc54d2219b132f3ae55"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ead20f7913a9c1e894aebe47cccf9dc834e1618b7aa96155d2091a626e59c972"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:ca49a8119c6cbd77375ae303b0cfd8c11f011abbbd64601167ecca18a87e7cdd"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:323ba25b92454adb36fa425dc5cf6f8f19f78948cbad2e7bc6cdf7b0d7982e59"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:1236ed0952fbd919c100bc839eaa4a39ebc397ed1c08a97fc45fee2a595aa1b3"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:729177eaf0aefca0994ce4cffe96ad3c75e377c7b6f4efa59ebf003b6d398716"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-win32.whl", hash = "sha256:804d99b24ad523a1fe18cc707bf741670332f7c7412e9d49cb5eab67e886b9b5"},
{file = "psycopg2_binary-2.9.9-cp38-cp38-win_amd64.whl", hash = "sha256:a6cdcc3ede532f4a4b96000b6362099591ab4a3e913d70bcbac2b56c872446f7"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:72dffbd8b4194858d0941062a9766f8297e8868e1dd07a7b36212aaa90f49472"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:30dcc86377618a4c8f3b72418df92e77be4254d8f89f14b8e8f57d6d43603c0f"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:31a34c508c003a4347d389a9e6fcc2307cc2150eb516462a7a17512130de109e"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:15208be1c50b99203fe88d15695f22a5bed95ab3f84354c494bcb1d08557df67"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1873aade94b74715be2246321c8650cabf5a0d098a95bab81145ffffa4c13876"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3a58c98a7e9c021f357348867f537017057c2ed7f77337fd914d0bedb35dace7"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:4686818798f9194d03c9129a4d9a702d9e113a89cb03bffe08c6cf799e053291"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:ebdc36bea43063116f0486869652cb2ed7032dbc59fbcb4445c4862b5c1ecf7f"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:ca08decd2697fdea0aea364b370b1249d47336aec935f87b8bbfd7da5b2ee9c1"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ac05fb791acf5e1a3e39402641827780fe44d27e72567a000412c648a85ba860"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-win32.whl", hash = "sha256:9dba73be7305b399924709b91682299794887cbbd88e38226ed9f6712eabee90"},
{file = "psycopg2_binary-2.9.9-cp39-cp39-win_amd64.whl", hash = "sha256:f7ae5d65ccfbebdfa761585228eb4d0df3a8b15cfb53bd953e713e09fbb12957"},
]
[[package]]
name = "pyarrow"
version = "13.0.0"
version = "14.0.0"
description = "Python library for Apache Arrow"
category = "main"
optional = false
python-versions = ">=3.8"
files = [
{file = "pyarrow-13.0.0-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:1afcc2c33f31f6fb25c92d50a86b7a9f076d38acbcb6f9e74349636109550148"},
{file = "pyarrow-13.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:70fa38cdc66b2fc1349a082987f2b499d51d072faaa6b600f71931150de2e0e3"},
{file = "pyarrow-13.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cd57b13a6466822498238877892a9b287b0a58c2e81e4bdb0b596dbb151cbb73"},
{file = "pyarrow-13.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8ce69f7bf01de2e2764e14df45b8404fc6f1a5ed9871e8e08a12169f87b7a26"},
{file = "pyarrow-13.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:588f0d2da6cf1b1680974d63be09a6530fd1bd825dc87f76e162404779a157dc"},
{file = "pyarrow-13.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:6241afd72b628787b4abea39e238e3ff9f34165273fad306c7acf780dd850956"},
{file = "pyarrow-13.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:fda7857e35993673fcda603c07d43889fca60a5b254052a462653f8656c64f44"},
{file = "pyarrow-13.0.0-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:aac0ae0146a9bfa5e12d87dda89d9ef7c57a96210b899459fc2f785303dcbb67"},
{file = "pyarrow-13.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d7759994217c86c161c6a8060509cfdf782b952163569606bb373828afdd82e8"},
{file = "pyarrow-13.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:868a073fd0ff6468ae7d869b5fc1f54de5c4255b37f44fb890385eb68b68f95d"},
{file = "pyarrow-13.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:51be67e29f3cfcde263a113c28e96aa04362ed8229cb7c6e5f5c719003659d33"},
{file = "pyarrow-13.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:d1b4e7176443d12610874bb84d0060bf080f000ea9ed7c84b2801df851320295"},
{file = "pyarrow-13.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:69b6f9a089d116a82c3ed819eea8fe67dae6105f0d81eaf0fdd5e60d0c6e0944"},
{file = "pyarrow-13.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:ab1268db81aeb241200e321e220e7cd769762f386f92f61b898352dd27e402ce"},
{file = "pyarrow-13.0.0-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:ee7490f0f3f16a6c38f8c680949551053c8194e68de5046e6c288e396dccee80"},
{file = "pyarrow-13.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e3ad79455c197a36eefbd90ad4aa832bece7f830a64396c15c61a0985e337287"},
{file = "pyarrow-13.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68fcd2dc1b7d9310b29a15949cdd0cb9bc34b6de767aff979ebf546020bf0ba0"},
{file = "pyarrow-13.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dc6fd330fd574c51d10638e63c0d00ab456498fc804c9d01f2a61b9264f2c5b2"},
{file = "pyarrow-13.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:e66442e084979a97bb66939e18f7b8709e4ac5f887e636aba29486ffbf373763"},
{file = "pyarrow-13.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:0f6eff839a9e40e9c5610d3ff8c5bdd2f10303408312caf4c8003285d0b49565"},
{file = "pyarrow-13.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:8b30a27f1cddf5c6efcb67e598d7823a1e253d743d92ac32ec1eb4b6a1417867"},
{file = "pyarrow-13.0.0-cp39-cp39-macosx_10_14_x86_64.whl", hash = "sha256:09552dad5cf3de2dc0aba1c7c4b470754c69bd821f5faafc3d774bedc3b04bb7"},
{file = "pyarrow-13.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3896ae6c205d73ad192d2fc1489cd0edfab9f12867c85b4c277af4d37383c18c"},
{file = "pyarrow-13.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6647444b21cb5e68b593b970b2a9a07748dd74ea457c7dadaa15fd469c48ada1"},
{file = "pyarrow-13.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47663efc9c395e31d09c6aacfa860f4473815ad6804311c5433f7085415d62a7"},
{file = "pyarrow-13.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:b9ba6b6d34bd2563345488cf444510588ea42ad5613df3b3509f48eb80250afd"},
{file = "pyarrow-13.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:d00d374a5625beeb448a7fa23060df79adb596074beb3ddc1838adb647b6ef09"},
{file = "pyarrow-13.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:c51afd87c35c8331b56f796eff954b9c7f8d4b7fef5903daf4e05fcf017d23a8"},
{file = "pyarrow-13.0.0.tar.gz", hash = "sha256:83333726e83ed44b0ac94d8d7a21bbdee4a05029c3b1e8db58a863eec8fd8a33"},
{file = "pyarrow-14.0.0-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:4fce1db17efbc453080c5b306f021926de7c636456a128328797e574c151f81a"},
{file = "pyarrow-14.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:28de7c05b4d7a71ec660360639cc9b65ceb1175e0e9d4dfccd879a1545bc38f7"},
{file = "pyarrow-14.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1541e9209c094e7f4d7b43fdd9de3a8c71d3069cf6fc03b59bf5774042411849"},
{file = "pyarrow-14.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8c05e6c45d303c80e41ab04996430a0251321f70986ed51213903ea7bc0b7efd"},
{file = "pyarrow-14.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:426ffec63ab9b4dff23dec51be2150e3a4a99eb38e66c10a70e2c48779fe9c9d"},
{file = "pyarrow-14.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:968844f591902160bd3c9ee240ce8822a3b4e7de731e91daea76ad43fe0ff062"},
{file = "pyarrow-14.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:dcedbc0b4ea955c530145acfe99e324875c386419a09db150291a24cb01aeb81"},
{file = "pyarrow-14.0.0-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:97993a12aacc781efad9c92d4545a877e803c4d106d34237ec4ce987bec825a3"},
{file = "pyarrow-14.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:80225768d94024d59a31320374f5e6abf8899866c958dfb4f4ea8e2d9ec91bde"},
{file = "pyarrow-14.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b61546977a8bd7e3d0c697ede723341ef4737e761af2239aef6e1db447f97727"},
{file = "pyarrow-14.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42509e6c93b4a1c8ae8ccd939a43f437097783fe130a1991497a6a1abbba026f"},
{file = "pyarrow-14.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:3eccce331a1392e46573f2ce849a9ee3c074e0d7008e9be0b44566ac149fd6a1"},
{file = "pyarrow-14.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:ecc463c45f2b6b36431f5f2025842245e8c15afe4d42072230575785f3bb00c6"},
{file = "pyarrow-14.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:4362ed90def81640addcd521811dd16a13015f0a8255bec324a41262c1524b6c"},
{file = "pyarrow-14.0.0-cp312-cp312-macosx_10_14_x86_64.whl", hash = "sha256:2fbb7ab62537782c5ab31aa08db0e1f6de92c2c515fdfc0790128384e919adcb"},
{file = "pyarrow-14.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ad7095f8f0fe0bfa3d3fca1909b8fa15c70e630b0cc1ff8d35e143f5e2704064"},
{file = "pyarrow-14.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e6602272fce71c0fb64f266e7cdbe51b93b00c22fc1bb57f2b0cb681c4aeedf4"},
{file = "pyarrow-14.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5b2b8f87951b08a3e72265c8963da3fe4f737bb81290269037e047dd172aa591"},
{file = "pyarrow-14.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:a1c9675966662a042caebbaafa1ae7fc26291287ebc3da06aa63ad74c323ec30"},
{file = "pyarrow-14.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:771079fddc0b4440c41af541dbdebc711a7062c93d3c4764476a9442606977db"},
{file = "pyarrow-14.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:c4096136318de1c4937370c0c365f949961c371201c396d8cc94a353f342069d"},
{file = "pyarrow-14.0.0-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:6c94056fb5f0ee0bae2206c3f776881e1db2bd0d133d06805755ae7ac5145349"},
{file = "pyarrow-14.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:687d0df1e08876b2d24d42abae129742fc655367e3fe6700aa4d79fcf2e3215e"},
{file = "pyarrow-14.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0f4054e5ee6c88ca256a67fc8b27f9c59bcd385216346265831d462a6069033f"},
{file = "pyarrow-14.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:768b962e4c042ab2c96576ca0757935472e220d11af855c7d0be3279d7fced5f"},
{file = "pyarrow-14.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:77293b1319c7044f68ebfa43db8c929a0a5254ce371f1a0873d343f1460171d0"},
{file = "pyarrow-14.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:d2bc7c53941d85f0133b1bd5a814bca0af213922f50d8a8dc0eed4d9ed477845"},
{file = "pyarrow-14.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:378955365dd087c285ef4f34ad939d7e551b7715326710e8cd21cfa2ce511bd7"},
{file = "pyarrow-14.0.0-cp39-cp39-macosx_10_14_x86_64.whl", hash = "sha256:f05e81b4c621e6ad4bcd8f785e3aa1d6c49a935818b809ea6e7bf206a5b1a4e8"},
{file = "pyarrow-14.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6867f6a8057eaef5a7ac6d27fe5518133f67973c5d4295d79a943458350e7c61"},
{file = "pyarrow-14.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ca54b87c46abdfe027f18f959ca388102bd7326c344838f72244807462d091b2"},
{file = "pyarrow-14.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:35abf61bd0cc9daca3afc715f6ba74ea83d792fa040025352624204bec66bf6a"},
{file = "pyarrow-14.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:65c377523b369f7ef1ba02be814e832443bb3b15065010838f02dae5bdc0f53c"},
{file = "pyarrow-14.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:e8a1e470e4b5f7bda7bede0410291daec55ab69f346d77795d34fd6a45b41579"},
{file = "pyarrow-14.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:466c1a5a7a4b279cfa363ac34dedd0c3c6af388cec9e6a468ffc095a6627849a"},
{file = "pyarrow-14.0.0.tar.gz", hash = "sha256:45d3324e1c9871a07de6b4d514ebd73225490963a6dd46c64c465c4b6079fe1e"},
]
[package.dependencies]
@@ -1909,14 +2111,14 @@ testing-integration = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "jar
[[package]]
name = "shellingham"
version = "1.5.3"
version = "1.5.4"
description = "Tool to Detect Surrounding Shell"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "shellingham-1.5.3-py2.py3-none-any.whl", hash = "sha256:419c6a164770c9c7cfcaeddfacb3d31ac7a8db0b0f3e9c1287679359734107e9"},
{file = "shellingham-1.5.3.tar.gz", hash = "sha256:cb4a6fec583535bc6da17b647dd2330cf7ef30239e05d547d99ae3705fd0f7f8"},
{file = "shellingham-1.5.4-py2.py3-none-any.whl", hash = "sha256:7ecfff8f2fd72616f7481040475a65b2bf8af90a56c89140852d1120324e8686"},
{file = "shellingham-1.5.4.tar.gz", hash = "sha256:8dbca0739d487e5bd35ab3ca4b36e11c4078f3a234bfce294b0a0291363404de"},
]
[[package]]
@@ -1945,61 +2147,61 @@ files = [
[[package]]
name = "sqlalchemy"
version = "2.0.22"
version = "2.0.23"
description = "Database Abstraction Library"
category = "main"
optional = false
python-versions = ">=3.7"
files = [
{file = "SQLAlchemy-2.0.22-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f146c61ae128ab43ea3a0955de1af7e1633942c2b2b4985ac51cc292daf33222"},
{file = "SQLAlchemy-2.0.22-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:875de9414393e778b655a3d97d60465eb3fae7c919e88b70cc10b40b9f56042d"},
{file = "SQLAlchemy-2.0.22-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:13790cb42f917c45c9c850b39b9941539ca8ee7917dacf099cc0b569f3d40da7"},
{file = "SQLAlchemy-2.0.22-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e04ab55cf49daf1aeb8c622c54d23fa4bec91cb051a43cc24351ba97e1dd09f5"},
{file = "SQLAlchemy-2.0.22-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:a42c9fa3abcda0dcfad053e49c4f752eef71ecd8c155221e18b99d4224621176"},
{file = "SQLAlchemy-2.0.22-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:14cd3bcbb853379fef2cd01e7c64a5d6f1d005406d877ed9509afb7a05ff40a5"},
{file = "SQLAlchemy-2.0.22-cp310-cp310-win32.whl", hash = "sha256:d143c5a9dada696bcfdb96ba2de4a47d5a89168e71d05a076e88a01386872f97"},
{file = "SQLAlchemy-2.0.22-cp310-cp310-win_amd64.whl", hash = "sha256:ccd87c25e4c8559e1b918d46b4fa90b37f459c9b4566f1dfbce0eb8122571547"},
{file = "SQLAlchemy-2.0.22-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4f6ff392b27a743c1ad346d215655503cec64405d3b694228b3454878bf21590"},
{file = "SQLAlchemy-2.0.22-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f776c2c30f0e5f4db45c3ee11a5f2a8d9de68e81eb73ec4237de1e32e04ae81c"},
{file = "SQLAlchemy-2.0.22-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c8f1792d20d2f4e875ce7a113f43c3561ad12b34ff796b84002a256f37ce9437"},
{file = "SQLAlchemy-2.0.22-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d80eeb5189d7d4b1af519fc3f148fe7521b9dfce8f4d6a0820e8f5769b005051"},
{file = "SQLAlchemy-2.0.22-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:69fd9e41cf9368afa034e1c81f3570afb96f30fcd2eb1ef29cb4d9371c6eece2"},
{file = "SQLAlchemy-2.0.22-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:54bcceaf4eebef07dadfde424f5c26b491e4a64e61761dea9459103ecd6ccc95"},
{file = "SQLAlchemy-2.0.22-cp311-cp311-win32.whl", hash = "sha256:7ee7ccf47aa503033b6afd57efbac6b9e05180f492aeed9fcf70752556f95624"},
{file = "SQLAlchemy-2.0.22-cp311-cp311-win_amd64.whl", hash = "sha256:b560f075c151900587ade06706b0c51d04b3277c111151997ea0813455378ae0"},
{file = "SQLAlchemy-2.0.22-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:2c9bac865ee06d27a1533471405ad240a6f5d83195eca481f9fc4a71d8b87df8"},
{file = "SQLAlchemy-2.0.22-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:625b72d77ac8ac23da3b1622e2da88c4aedaee14df47c8432bf8f6495e655de2"},
{file = "SQLAlchemy-2.0.22-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b39a6e21110204a8c08d40ff56a73ba542ec60bab701c36ce721e7990df49fb9"},
{file = "SQLAlchemy-2.0.22-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:53a766cb0b468223cafdf63e2d37f14a4757476157927b09300c8c5832d88560"},
{file = "SQLAlchemy-2.0.22-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:0e1ce8ebd2e040357dde01a3fb7d30d9b5736b3e54a94002641dfd0aa12ae6ce"},
{file = "SQLAlchemy-2.0.22-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:505f503763a767556fa4deae5194b2be056b64ecca72ac65224381a0acab7ebe"},
{file = "SQLAlchemy-2.0.22-cp312-cp312-win32.whl", hash = "sha256:154a32f3c7b00de3d090bc60ec8006a78149e221f1182e3edcf0376016be9396"},
{file = "SQLAlchemy-2.0.22-cp312-cp312-win_amd64.whl", hash = "sha256:129415f89744b05741c6f0b04a84525f37fbabe5dc3774f7edf100e7458c48cd"},
{file = "SQLAlchemy-2.0.22-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3940677d341f2b685a999bffe7078697b5848a40b5f6952794ffcf3af150c301"},
{file = "SQLAlchemy-2.0.22-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:55914d45a631b81a8a2cb1a54f03eea265cf1783241ac55396ec6d735be14883"},
{file = "SQLAlchemy-2.0.22-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2096d6b018d242a2bcc9e451618166f860bb0304f590d205173d317b69986c95"},
{file = "SQLAlchemy-2.0.22-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:19c6986cf2fb4bc8e0e846f97f4135a8e753b57d2aaaa87c50f9acbe606bd1db"},
{file = "SQLAlchemy-2.0.22-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:6ac28bd6888fe3c81fbe97584eb0b96804bd7032d6100b9701255d9441373ec1"},
{file = "SQLAlchemy-2.0.22-cp37-cp37m-win32.whl", hash = "sha256:cb9a758ad973e795267da334a92dd82bb7555cb36a0960dcabcf724d26299db8"},
{file = "SQLAlchemy-2.0.22-cp37-cp37m-win_amd64.whl", hash = "sha256:40b1206a0d923e73aa54f0a6bd61419a96b914f1cd19900b6c8226899d9742ad"},
{file = "SQLAlchemy-2.0.22-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:3aa1472bf44f61dd27987cd051f1c893b7d3b17238bff8c23fceaef4f1133868"},
{file = "SQLAlchemy-2.0.22-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:56a7e2bb639df9263bf6418231bc2a92a773f57886d371ddb7a869a24919face"},
{file = "SQLAlchemy-2.0.22-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ccca778c0737a773a1ad86b68bda52a71ad5950b25e120b6eb1330f0df54c3d0"},
{file = "SQLAlchemy-2.0.22-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c6c3e9350f9fb16de5b5e5fbf17b578811a52d71bb784cc5ff71acb7de2a7f9"},
{file = "SQLAlchemy-2.0.22-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:564e9f9e4e6466273dbfab0e0a2e5fe819eec480c57b53a2cdee8e4fdae3ad5f"},
{file = "SQLAlchemy-2.0.22-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:af66001d7b76a3fab0d5e4c1ec9339ac45748bc4a399cbc2baa48c1980d3c1f4"},
{file = "SQLAlchemy-2.0.22-cp38-cp38-win32.whl", hash = "sha256:9e55dff5ec115316dd7a083cdc1a52de63693695aecf72bc53a8e1468ce429e5"},
{file = "SQLAlchemy-2.0.22-cp38-cp38-win_amd64.whl", hash = "sha256:4e869a8ff7ee7a833b74868a0887e8462445ec462432d8cbeff5e85f475186da"},
{file = "SQLAlchemy-2.0.22-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9886a72c8e6371280cb247c5d32c9c8fa141dc560124348762db8a8b236f8692"},
{file = "SQLAlchemy-2.0.22-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a571bc8ac092a3175a1d994794a8e7a1f2f651e7c744de24a19b4f740fe95034"},
{file = "SQLAlchemy-2.0.22-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8db5ba8b7da759b727faebc4289a9e6a51edadc7fc32207a30f7c6203a181592"},
{file = "SQLAlchemy-2.0.22-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b0b3f2686c3f162123adba3cb8b626ed7e9b8433ab528e36ed270b4f70d1cdb"},
{file = "SQLAlchemy-2.0.22-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:0c1fea8c0abcb070ffe15311853abfda4e55bf7dc1d4889497b3403629f3bf00"},
{file = "SQLAlchemy-2.0.22-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4bb062784f37b2d75fd9b074c8ec360ad5df71f933f927e9e95c50eb8e05323c"},
{file = "SQLAlchemy-2.0.22-cp39-cp39-win32.whl", hash = "sha256:58a3aba1bfb32ae7af68da3f277ed91d9f57620cf7ce651db96636790a78b736"},
{file = "SQLAlchemy-2.0.22-cp39-cp39-win_amd64.whl", hash = "sha256:92e512a6af769e4725fa5b25981ba790335d42c5977e94ded07db7d641490a85"},
{file = "SQLAlchemy-2.0.22-py3-none-any.whl", hash = "sha256:3076740335e4aaadd7deb3fe6dcb96b3015f1613bd190a4e1634e1b99b02ec86"},
{file = "SQLAlchemy-2.0.22.tar.gz", hash = "sha256:5434cc601aa17570d79e5377f5fd45ff92f9379e2abed0be5e8c2fba8d353d2b"},
{file = "SQLAlchemy-2.0.23-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:638c2c0b6b4661a4fd264f6fb804eccd392745c5887f9317feb64bb7cb03b3ea"},
{file = "SQLAlchemy-2.0.23-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e3b5036aa326dc2df50cba3c958e29b291a80f604b1afa4c8ce73e78e1c9f01d"},
{file = "SQLAlchemy-2.0.23-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:787af80107fb691934a01889ca8f82a44adedbf5ef3d6ad7d0f0b9ac557e0c34"},
{file = "SQLAlchemy-2.0.23-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c14eba45983d2f48f7546bb32b47937ee2cafae353646295f0e99f35b14286ab"},
{file = "SQLAlchemy-2.0.23-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0666031df46b9badba9bed00092a1ffa3aa063a5e68fa244acd9f08070e936d3"},
{file = "SQLAlchemy-2.0.23-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:89a01238fcb9a8af118eaad3ffcc5dedaacbd429dc6fdc43fe430d3a941ff965"},
{file = "SQLAlchemy-2.0.23-cp310-cp310-win32.whl", hash = "sha256:cabafc7837b6cec61c0e1e5c6d14ef250b675fa9c3060ed8a7e38653bd732ff8"},
{file = "SQLAlchemy-2.0.23-cp310-cp310-win_amd64.whl", hash = "sha256:87a3d6b53c39cd173990de2f5f4b83431d534a74f0e2f88bd16eabb5667e65c6"},
{file = "SQLAlchemy-2.0.23-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d5578e6863eeb998980c212a39106ea139bdc0b3f73291b96e27c929c90cd8e1"},
{file = "SQLAlchemy-2.0.23-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:62d9e964870ea5ade4bc870ac4004c456efe75fb50404c03c5fd61f8bc669a72"},
{file = "SQLAlchemy-2.0.23-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c80c38bd2ea35b97cbf7c21aeb129dcbebbf344ee01a7141016ab7b851464f8e"},
{file = "SQLAlchemy-2.0.23-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75eefe09e98043cff2fb8af9796e20747ae870c903dc61d41b0c2e55128f958d"},
{file = "SQLAlchemy-2.0.23-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:bd45a5b6c68357578263d74daab6ff9439517f87da63442d244f9f23df56138d"},
{file = "SQLAlchemy-2.0.23-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a86cb7063e2c9fb8e774f77fbf8475516d270a3e989da55fa05d08089d77f8c4"},
{file = "SQLAlchemy-2.0.23-cp311-cp311-win32.whl", hash = "sha256:b41f5d65b54cdf4934ecede2f41b9c60c9f785620416e8e6c48349ab18643855"},
{file = "SQLAlchemy-2.0.23-cp311-cp311-win_amd64.whl", hash = "sha256:9ca922f305d67605668e93991aaf2c12239c78207bca3b891cd51a4515c72e22"},
{file = "SQLAlchemy-2.0.23-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d0f7fb0c7527c41fa6fcae2be537ac137f636a41b4c5a4c58914541e2f436b45"},
{file = "SQLAlchemy-2.0.23-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:7c424983ab447dab126c39d3ce3be5bee95700783204a72549c3dceffe0fc8f4"},
{file = "SQLAlchemy-2.0.23-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f508ba8f89e0a5ecdfd3761f82dda2a3d7b678a626967608f4273e0dba8f07ac"},
{file = "SQLAlchemy-2.0.23-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6463aa765cf02b9247e38b35853923edbf2f6fd1963df88706bc1d02410a5577"},
{file = "SQLAlchemy-2.0.23-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:e599a51acf3cc4d31d1a0cf248d8f8d863b6386d2b6782c5074427ebb7803bda"},
{file = "SQLAlchemy-2.0.23-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:fd54601ef9cc455a0c61e5245f690c8a3ad67ddb03d3b91c361d076def0b4c60"},
{file = "SQLAlchemy-2.0.23-cp312-cp312-win32.whl", hash = "sha256:42d0b0290a8fb0165ea2c2781ae66e95cca6e27a2fbe1016ff8db3112ac1e846"},
{file = "SQLAlchemy-2.0.23-cp312-cp312-win_amd64.whl", hash = "sha256:227135ef1e48165f37590b8bfc44ed7ff4c074bf04dc8d6f8e7f1c14a94aa6ca"},
{file = "SQLAlchemy-2.0.23-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:14aebfe28b99f24f8a4c1346c48bc3d63705b1f919a24c27471136d2f219f02d"},
{file = "SQLAlchemy-2.0.23-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e983fa42164577d073778d06d2cc5d020322425a509a08119bdcee70ad856bf"},
{file = "SQLAlchemy-2.0.23-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e0dc9031baa46ad0dd5a269cb7a92a73284d1309228be1d5935dac8fb3cae24"},
{file = "SQLAlchemy-2.0.23-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:5f94aeb99f43729960638e7468d4688f6efccb837a858b34574e01143cf11f89"},
{file = "SQLAlchemy-2.0.23-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:63bfc3acc970776036f6d1d0e65faa7473be9f3135d37a463c5eba5efcdb24c8"},
{file = "SQLAlchemy-2.0.23-cp37-cp37m-win32.whl", hash = "sha256:f48ed89dd11c3c586f45e9eec1e437b355b3b6f6884ea4a4c3111a3358fd0c18"},
{file = "SQLAlchemy-2.0.23-cp37-cp37m-win_amd64.whl", hash = "sha256:1e018aba8363adb0599e745af245306cb8c46b9ad0a6fc0a86745b6ff7d940fc"},
{file = "SQLAlchemy-2.0.23-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:64ac935a90bc479fee77f9463f298943b0e60005fe5de2aa654d9cdef46c54df"},
{file = "SQLAlchemy-2.0.23-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:c4722f3bc3c1c2fcc3702dbe0016ba31148dd6efcd2a2fd33c1b4897c6a19693"},
{file = "SQLAlchemy-2.0.23-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4af79c06825e2836de21439cb2a6ce22b2ca129bad74f359bddd173f39582bf5"},
{file = "SQLAlchemy-2.0.23-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:683ef58ca8eea4747737a1c35c11372ffeb84578d3aab8f3e10b1d13d66f2bc4"},
{file = "SQLAlchemy-2.0.23-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:d4041ad05b35f1f4da481f6b811b4af2f29e83af253bf37c3c4582b2c68934ab"},
{file = "SQLAlchemy-2.0.23-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:aeb397de65a0a62f14c257f36a726945a7f7bb60253462e8602d9b97b5cbe204"},
{file = "SQLAlchemy-2.0.23-cp38-cp38-win32.whl", hash = "sha256:42ede90148b73fe4ab4a089f3126b2cfae8cfefc955c8174d697bb46210c8306"},
{file = "SQLAlchemy-2.0.23-cp38-cp38-win_amd64.whl", hash = "sha256:964971b52daab357d2c0875825e36584d58f536e920f2968df8d581054eada4b"},
{file = "SQLAlchemy-2.0.23-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:616fe7bcff0a05098f64b4478b78ec2dfa03225c23734d83d6c169eb41a93e55"},
{file = "SQLAlchemy-2.0.23-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:0e680527245895aba86afbd5bef6c316831c02aa988d1aad83c47ffe92655e74"},
{file = "SQLAlchemy-2.0.23-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9585b646ffb048c0250acc7dad92536591ffe35dba624bb8fd9b471e25212a35"},
{file = "SQLAlchemy-2.0.23-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4895a63e2c271ffc7a81ea424b94060f7b3b03b4ea0cd58ab5bb676ed02f4221"},
{file = "SQLAlchemy-2.0.23-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:cc1d21576f958c42d9aec68eba5c1a7d715e5fc07825a629015fe8e3b0657fb0"},
{file = "SQLAlchemy-2.0.23-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:967c0b71156f793e6662dd839da54f884631755275ed71f1539c95bbada9aaab"},
{file = "SQLAlchemy-2.0.23-cp39-cp39-win32.whl", hash = "sha256:0a8c6aa506893e25a04233bc721c6b6cf844bafd7250535abb56cb6cc1368884"},
{file = "SQLAlchemy-2.0.23-cp39-cp39-win_amd64.whl", hash = "sha256:f3420d00d2cb42432c1d0e44540ae83185ccbbc67a6054dcc8ab5387add6620b"},
{file = "SQLAlchemy-2.0.23-py3-none-any.whl", hash = "sha256:31952bbc527d633b9479f5f81e8b9dfada00b91d6baba021a869095f1a97006d"},
{file = "SQLAlchemy-2.0.23.tar.gz", hash = "sha256:c1bda93cbbe4aa2aa0aa8655c5aeda505cd219ff3e8da91d1d329e143e4aff69"},
]
[package.dependencies]
@@ -2008,6 +2210,7 @@ typing-extensions = ">=4.2.0"
[package.extras]
aiomysql = ["aiomysql (>=0.2.0)", "greenlet (!=0.4.17)"]
aioodbc = ["aioodbc", "greenlet (!=0.4.17)"]
aiosqlite = ["aiosqlite", "greenlet (!=0.4.17)", "typing-extensions (!=3.10.0.1)"]
asyncio = ["greenlet (!=0.4.17)"]
asyncmy = ["asyncmy (>=0.2.3,!=0.2.4,!=0.2.6)", "greenlet (!=0.4.17)"]
@@ -2018,7 +2221,7 @@ mssql-pyodbc = ["pyodbc"]
mypy = ["mypy (>=0.910)"]
mysql = ["mysqlclient (>=1.4.0)"]
mysql-connector = ["mysql-connector-python"]
oracle = ["cx-oracle (>=7)"]
oracle = ["cx-oracle (>=8)"]
oracle-oracledb = ["oracledb (>=1.0.1)"]
postgresql = ["psycopg2 (>=2.7)"]
postgresql-asyncpg = ["asyncpg", "greenlet (!=0.4.17)"]
@@ -2208,14 +2411,14 @@ socks = ["PySocks (>=1.5.6,!=1.5.7,<2.0)"]
[[package]]
name = "wcwidth"
version = "0.2.8"
version = "0.2.9"
description = "Measures the displayed width of unicode strings in a terminal"
category = "main"
optional = false
python-versions = "*"
files = [
{file = "wcwidth-0.2.8-py2.py3-none-any.whl", hash = "sha256:77f719e01648ed600dfa5402c347481c0992263b81a027344f3e1ba25493a704"},
{file = "wcwidth-0.2.8.tar.gz", hash = "sha256:8705c569999ffbb4f6a87c6d1b80f324bd6db952f5eb0b95bc07517f4c1813d4"},
{file = "wcwidth-0.2.9-py2.py3-none-any.whl", hash = "sha256:9a929bd8380f6cd9571a968a9c8f4353ca58d7cd812a4822bba831f8d685b223"},
{file = "wcwidth-0.2.9.tar.gz", hash = "sha256:a675d1a4a2d24ef67096a04b85b02deeecd8e226f57b5e3a72dbb9ed99d27da8"},
]
[[package]]
@@ -2512,4 +2715,4 @@ multidict = ">=4.0"
[metadata]
lock-version = "2.0"
python-versions = "<3.12,>=3.9"
content-hash = "13e73dc8fe9e19792903e9659b53cfa24bcc7abbd73fd0d691daeb22136cdaa0"
content-hash = "abe2ac60310fb50945a1c4df18fa3fb70a3e7d86886b448726dec49f01e8af7d"

4
pyproject.toml
View File

@@ -36,6 +36,10 @@ llama-index = "^0.8.53.post3"
setuptools = "^68.2.2"
datasets = "^2.14.6"
prettytable = "^3.9.0"
pgvector = "^0.2.3"
psycopg = "^3.1.12"
psycopg-binary = "^3.1.12"
psycopg2-binary = "^2.9.9"
[build-system]

0
tests/__init__.py Normal file
View File

1
tests/constants.py Normal file
View File

@@ -0,0 +1 @@
TIMEOUT = 30 # seconds

47
tests/test_cli.py Normal file
View File

@@ -0,0 +1,47 @@
import subprocess
import sys
subprocess.check_call([sys.executable, "-m", "pip", "install", "pexpect"])
import pexpect
from .constants import TIMEOUT
from .utils import configure_memgpt
def test_configure_memgpt():
configure_memgpt()
def test_save_load():
configure_memgpt()
child = pexpect.spawn("memgpt run --agent test_save_load --first --strip_ui")
child.expect("Enter your message:", timeout=TIMEOUT)
child.sendline()
child.expect("Empty input received. Try again!", timeout=TIMEOUT)
child.sendline("/save")
child.expect("Saved local", timeout=TIMEOUT)
child.expect("Enter your message:", timeout=TIMEOUT)
child.sendline("/exit")
child.expect(pexpect.EOF, timeout=TIMEOUT) # Wait for child to exit
child.close()
assert child.isalive() is False, "CLI should have terminated."
assert child.exitstatus == 0, "CLI did not exit cleanly."
child = pexpect.spawn("memgpt run --agent test_save_load --first --strip_ui")
child.expect("Using existing agent test_save_load", timeout=TIMEOUT)
child.expect("Enter your message:", timeout=TIMEOUT)
child.sendline("/exit")
child.expect(pexpect.EOF, timeout=TIMEOUT) # Wait for child to exit
child.close()
assert child.isalive() is False, "CLI should have terminated."
assert child.exitstatus == 0, "CLI did not exit cleanly."
if __name__ == "__main__":
test_configure_memgpt()
test_save_load()
# test_legacy_cli_sequence()

86
tests/test_load_archival.py
View File

@@ -1,11 +1,13 @@
# import tempfile
# import asyncio
# import os
# import asyncio
# from datasets import load_dataset
import os
# import asyncio
from datasets import load_dataset
import memgpt
from memgpt.cli.cli_load import load_directory, load_database, load_webpage
# import memgpt
# from memgpt.cli.cli_load import load_directory, load_database, load_webpage
# import memgpt.presets as presets
# import memgpt.personas.personas as personas
# import memgpt.humans.humans as humans
@@ -16,6 +18,80 @@
# import memgpt.interface # for printing to terminal
def test_postgres():
return
# override config path with enviornment variable
# TODO: make into temporary file
os.environ["MEMGPT_CONFIG_PATH"] = "test_config.cfg"
print("env", os.getenv("MEMGPT_CONFIG_PATH"))
config = memgpt.config.MemGPTConfig(archival_storage_type="postgres", config_path=os.getenv("MEMGPT_CONFIG_PATH"))
print(config)
config.save()
# exit()
name = "tmp_hf_dataset2"
dataset = load_dataset("MemGPT/example_short_stories")
cache_dir = os.getenv("HF_DATASETS_CACHE")
if cache_dir is None:
# Construct the default path if the environment variable is not set.
cache_dir = os.path.join(os.path.expanduser("~"), ".cache", "huggingface", "datasets")
load_directory(
name=name,
input_dir=cache_dir,
recursive=True,
)
def test_chroma():
return
subprocess.check_call([sys.executable, "-m", "pip", "install", "chromadb"])
import chromadb # Try to import again after installing
# override config path with enviornment variable
# TODO: make into temporary file
os.environ["MEMGPT_CONFIG_PATH"] = "test_config.cfg"
print("env", os.getenv("MEMGPT_CONFIG_PATH"))
config = memgpt.config.MemGPTConfig(archival_storage_type="chroma", config_path=os.getenv("MEMGPT_CONFIG_PATH"))
print(config)
config.save()
# exit()
name = "tmp_hf_dataset"
dataset = load_dataset("MemGPT/example_short_stories")
cache_dir = os.getenv("HF_DATASETS_CACHE")
if cache_dir is None:
# Construct the default path if the environment variable is not set.
cache_dir = os.path.join(os.path.expanduser("~"), ".cache", "huggingface", "datasets")
config = memgpt.config.MemGPTConfig(archival_storage_type="chroma")
load_directory(
name=name,
input_dir=cache_dir,
recursive=True,
)
# index = memgpt.embeddings.Index(name)
## query chroma
##chroma_client = chromadb.Client()
# chroma_client = chromadb.PersistentClient(path="/Users/sarahwooders/repos/MemGPT/chromadb")
# collection = chroma_client.get_collection(name=name)
# results = collection.query(
# query_texts=["cinderella be getting sick"],
# n_results=2
# )
# print(results)
# assert len(results) == 2, f"Expected 2 results, but got {len(results)}"
def test_load_directory():
return
# downloading hugging face dataset (if does not exist)

4
tests/test_questionary.py
View File

@@ -1,3 +1,7 @@
import subprocess
import sys
subprocess.check_call([sys.executable, "-m", "pip", "install", "pexpect"])
import pexpect

49
tests/test_storage.py Normal file
View File

@@ -0,0 +1,49 @@
import os
import subprocess
import sys
subprocess.check_call(
[sys.executable, "-m", "pip", "install", "pgvector", "psycopg", "psycopg2-binary"]
) # , "psycopg_binary"]) # "psycopg", "libpq-dev"])
import pgvector # Try to import again after installing
from memgpt.connectors.storage import StorageConnector, Passage
from memgpt.connectors.db import PostgresStorageConnector
from memgpt.embeddings import embedding_model
from memgpt.config import MemGPTConfig, AgentConfig
import argparse
def test_postgres():
config = MemGPTConfig()
config.archival_storage_uri = os.getenv("PGVECTOR_TEST_DB_URL") # the URI for a postgres DB w/ the pgvector extension
assert config.archival_storage_uri is not None
config.archival_storage_uri.replace("postgres://", "postgresql://") # https://stackoverflow.com/a/64698899
config.save()
print(config)
embed_model = embedding_model()
passage = ["This is a test passage", "This is another test passage", "Cinderella wept"]
db = PostgresStorageConnector(name="test2")
for passage in passage:
db.insert(Passage(text=passage, embedding=embed_model.get_text_embedding(passage)))
print(db.get_all())
query = "why was she crying"
query_vec = embed_model.get_text_embedding(query)
res = db.query(None, query_vec, top_k=2)
assert len(res) == 2, f"Expected 2 results, got {len(res)}"
assert "wept" in res[0].text, f"Expected 'wept' in results, but got {res[0].text}"
print("deleting...")
db.delete()
print("...finished")
test_postgres()

36
tests/utils.py Normal file
View File

@@ -0,0 +1,36 @@
import pexpect
from .constants import TIMEOUT
def configure_memgpt(enable_openai=True, enable_azure=False):
child = pexpect.spawn("memgpt configure")
child.expect("Do you want to enable MemGPT with Open AI?", timeout=TIMEOUT)
if enable_openai:
child.sendline("y")
else:
child.sendline("n")
child.expect("Do you want to enable MemGPT with Azure?", timeout=TIMEOUT)
if enable_azure:
child.sendline("y")
else:
child.sendline("n")
child.expect("Select default preset:", timeout=TIMEOUT)
child.sendline()
child.expect("Select default persona:", timeout=TIMEOUT)
child.sendline()
child.expect("Select default human:", timeout=TIMEOUT)
child.sendline()
child.expect("Select storage backend for archival data:", timeout=TIMEOUT)
child.sendline()
child.expect(pexpect.EOF, timeout=TIMEOUT) # Wait for child to exit
child.close()
assert child.isalive() is False, "CLI should have terminated."
assert child.exitstatus == 0, "CLI did not exit cleanly."