tombedor
c8e8557c27
fix: set json loads strict to false ( #946 )
2024-01-31 15:50:08 -08:00
Charles Packer
5112f5e161
fix: use utf-8 encodings for all text files ( #918 )
2024-01-30 11:59:58 -08:00
Adam
405b3429a0
fix: Enhancements in CommonVector and test_server for Handling Data ( #933 )
2024-01-27 16:46:23 -08:00
Sarah Wooders
2a0bd9e1f3
fix: Check existing of migrated agents and sources in tests + fix migrated agent saving bug ( #911 )
2024-01-23 11:55:42 -08:00
Sarah Wooders
35b48c5fc0
fix: add Annotated to CLI options ( #906 )
...
Co-authored-by: Charles Packer <packercharles@gmail.com >
2024-01-23 11:27:24 -08:00
tombedor
570dc2a893
fix: simplify user config ( #904 )
2024-01-22 19:25:03 -08:00
Charles Packer
08d5fe8edd
refactor: refactor MemGPT + AutoGen integration to work with MemGPT 0.2.12+ (DB release) ( #905 )
2024-01-22 17:49:48 -08:00
starsnatched
4c95b7bde3
feat: Benchmark Command: memgpt benchmark ( #816 )
...
Co-authored-by: Starlette <starlette@Starlettes-MacBook-Pro.local >
Co-authored-by: cpacker <packercharles@gmail.com >
2024-01-21 00:57:01 -08:00
RT
1f7f5384fb
fix: Remove the hard-coded database URI in the test helper to use an env var ( #865 )
2024-01-20 22:56:46 -08:00
Sarah Wooders
45edc624d8
fix: Add tests for migration code and bugfix for pulling LLM/embedding configs from user instead of config ( #878 )
...
Co-authored-by: cpacker <packercharles@gmail.com >
2024-01-20 22:30:08 -08:00
Sarah Wooders
73c9f8547f
fix: minor fixes to allow tests to pass without OPENAI_API_KEY set ( #871 )
2024-01-20 15:07:16 -08:00
Sarah Wooders
4039763de5
feat: Store embeddings padded to size 4096 to allow DB storage of varying size embeddings ( #852 )
...
Co-authored-by: cpacker <packercharles@gmail.com >
2024-01-19 16:03:13 -08:00
Sarah Wooders
1c93697ed2
feat: Helper script for clearing out test database for postgres ( #863 )
2024-01-19 15:31:40 -08:00
Charles Packer
da5a8cdbfe
refactor: remove User LLM/embed. defaults, add credentials file, add authentication option for custom LLM backends ( #835 )
2024-01-18 16:11:35 -08:00
Sarah Wooders
2f7ccb1807
feat: Get in-context Message.id values from server ( #851 )
2024-01-18 12:42:55 -08:00
RT
61897921fd
build: Update all actions to use cached poetry builds ( #846 )
2024-01-18 10:31:12 -08:00
Maximilian Winter
74c0d9af9d
feat: Support pydantic models as parameters to custom functions ( #839 )
...
Co-authored-by: cpacker <packercharles@gmail.com >
2024-01-17 17:21:00 -08:00
Charles Packer
c07746b097
refactor: Use Message types inside Agent state (agent.messages), enabling immediate tracking of Message objects ( #836 )
...
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com >
2024-01-17 17:02:56 -08:00
Sarah Wooders
9da53d1e1a
fix: Remove usage of config.anon_clientid ( #837 )
2024-01-16 20:37:58 -08:00
Sarah Wooders
92bbf83fc9
feat: Cursor-based pagination for storage connectors and server ( #830 )
2024-01-16 14:45:20 -08:00
Sarah Wooders
f47e800982
feat: Add paginated memory queries ( #825 )
...
Co-authored-by: cpacker <packercharles@gmail.com >
2024-01-15 21:21:58 -08:00
cpacker
78534f4852
fix: patched another test that used dummy user_id's to instead use the default user_id
2024-01-15 14:07:57 -08:00
cpacker
5799d4ab36
fix: patched another test that used dummy user_id's to instead use the default user_id
2024-01-15 14:03:39 -08:00
cpacker
41f9640364
fix: fixed the type hints in server to use uuid, patched tests that used strings as dummy users
2024-01-15 14:01:06 -08:00
ifsheldon
dd2f4fc873
fix: Turn off all ensure_ascii of json.dumps ( #800 )
2024-01-11 23:54:35 -08:00
Charles Packer
f118e01ad1
feat: Migration command for importing old agents into new DB backend ( #802 )
...
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com >
2024-01-11 14:57:21 -08:00
Max Blackmer
10865a4cb8
Merge branch 'main' into feature/global-logging
...
# Conflicts:
# memgpt/config.py
2024-01-11 11:12:03 -05:00
Max Blackmer
abf4fb03bd
[cpacker#319] fixed error with config with improper include in config.py
...
added test_log.py. for testing global logging in log.py
2024-01-11 10:44:20 -05:00
Charles Packer
f045c3515c
feat: add_function and remove_function commands ( #784 )
2024-01-10 23:19:14 -08:00
Charles Packer
771eeb6a02
fix: deprecate AgentConfig in favor of AgentState. ( #803 )
2024-01-10 20:23:47 -08:00
Tom Bedor
0c0f269453
feat: add_function and remove_function commands
...
Allows for dynamic editing of user defined functions.
Disallows removing functions that are defined by MemGPT itself.
2024-01-11 00:38:40 +00:00
Sarah Wooders
d118774bb7
fix: tests should only use "openai" quickstart if `OPENAI_API_KEY is set ( #801 )
2024-01-09 19:13:16 -08:00
Sarah Wooders
d331c71ec3
remove AgentConfig imports
2024-01-09 11:38:46 -08:00
Sarah Wooders
54fa07da7a
refactor!: Migrate users + agent information into storage connectors ( #785 )
...
Co-authored-by: cpacker <packercharles@gmail.com >
2024-01-08 15:59:49 -08:00
cpacker
e175c204b2
try another patch to recreate declarative base
2024-01-04 11:33:44 -08:00
cpacker
5b4875834f
Add extra code for wiping sqlalchemy globals
2024-01-04 11:26:35 -08:00
Sarah Wooders
ed101934da
Avoid usage of Vector type for when not using postgres
2024-01-04 09:23:04 -08:00
Sarah Wooders
8b5fe4f383
Avoid usage of Vector type for when not using postgres
2024-01-04 09:11:23 -08:00
Sarah Wooders
45e6d5793d
Modify tests to use openai quickstart
2024-01-03 19:01:27 -08:00
cpacker
d0ef339a4a
use --all-extras in poetry install for tests
2024-01-02 22:18:17 -08:00
cpacker
1f6af59e9d
added a new test that makes sure the base functions are working
2024-01-02 18:20:54 -08:00
Sarah Wooders
9bd524d70a
Move test_cli.py to use quickstart client
2024-01-02 17:13:25 -08:00
Sarah Wooders
e93dae02e7
Update CLI tests to use OpenAI pre-configured config
2024-01-02 16:14:22 -08:00
Charles Packer
b487366f21
Merge branch 'main' into cherry-pick-storage-refactor
2023-12-30 21:38:58 -08:00
BabellDev
b2e9a24671
feat: Add MemGPT "Python Client" ( #713 )
...
* First commit of memgpt client and some messy test code
* rolled back unnecessary changes to abstract interface; switched client to always use Queueing Interface
* Added missing interface clear() in run_command; added convenience method for checking if an agent exists, used that in create_agent
* Formatting fixes
* Fixed incorrect naming of get_agent_memory in rest server
* Removed erroneous clear from client save method; Replaced print statements with appropriate logger calls in server
* Updated readme with client usage instructions
* added tests for Client
* make printing to terminal togglable on queininginterface (should probably refactor this to a logger)
* turn off printing to stdout via interface by default
* allow importing the python client in a similar fashion to openai-python (see https://github.com/openai/openai-python )
* Allowed quickstart on init of client; updated readme and test_client accordingly
* oops, fixed name of openai_api_key config key
* Fixed small typo
* Fixed broken test by adding memgpt hosted model details to agent config
* silence llamaindex 'LLM is explicitly disabled. Using MockLLM.' on server
* default to openai if user's memgpt directory is empty (first time)
* correct type hint
* updated section on client in readme
* added comment about how MemGPT config != Agent config
* patch unrelated test
* update wording on readme
* patch another unrelated test
* added python client to readme docs
* Changed 'user' to 'human' in example; Defaulted AgentConfig.model to 'None'; Fixed issue in create_agent (accounting for dict config); matched test code to example
* Fixed advanced example
* patch test
* patch
---------
Co-authored-by: cpacker <packercharles@gmail.com >
2023-12-30 12:43:46 -08:00
Charles Packer
0b9fdcf46c
fix: added new json test case + added fix for it (also refactored clean json func) ( #739 )
2023-12-28 23:01:45 -08:00
Sarah Wooders
5f554d305b
Increase workflow test timeout time + add test prints
2023-12-27 15:42:11 +04:00
Sarah Wooders
515d9d0f62
Fix bug with chroma vector query
2023-12-27 14:40:11 +04:00
Sarah Wooders
3f8b9063a1
Run black formatter
2023-12-26 17:53:57 +04:00
Sarah Wooders
0c2bf05406
Bugfixes for get_all function and code cleanup to match main
2023-12-26 17:50:49 +04:00