Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity
1,070 Commits 1 Branch 0 Tags
a80b7e8fecdb97a17cbf720fbda7a27dbbeefdf7
Commit Graph

68 Commits

Author SHA1 Message Date
Charles Packer
b35de11d96 chore: run autoflake + isort (#1279) 2024-04-20 11:40:22 -07:00
Charles Packer
703ea47d72 feat: add Google AI Gemini Pro support (#1209) 2024-04-10 19:43:44 -07:00
Sarah Wooders
e58ca5baed feat: add remaining Python client support for REST API routes + tests (#1160) 2024-03-17 17:34:37 -07:00
Charles Packer
e93d41b57a feat: add archival memory GET, POST, DEL to REST API (#1119) 2024-03-09 14:23:36 -08:00
Charles Packer
637cb9c2b4 feat: one time pass of autoflake + add autoflake to dev extras (#1097) 
Co-authored-by: tombedor <tombedor@gmail.com>
 2024-03-05 16:35:12 -08:00
tombedor
1097eee7ab fix: configure black (#1072) 2024-02-29 15:19:08 -08:00
Sarah Wooders
4cdd9ee01f feat: refactor loading and attaching data sources, and upgrade to llama-index==0.10.6 (#1016) 2024-02-18 16:57:01 -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
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
Tom Bedor
4240012b7b fix: fix typo in memory.py 2024-01-15 13:54:13 -08:00
Sarah Wooders
e4a18c374e passing tests 2024-01-10 20:20:16 -08:00
Sarah Wooders
2f84caa817 fix archival reference 2024-01-10 19:47:39 -08:00
Sarah Wooders
841d47c462 Remove usage of agent_config from agent.py 2024-01-09 11:22:39 -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
Sarah Wooders
5de2557738 Fix bug with supporting paginated search for recall memory 2024-01-03 18:32:13 -08:00
Sarah Wooders
17506b7e90 Change Message data type to use tool format and create tool_call_id field 2024-01-03 18:03:11 -08:00
Charles Packer
b487366f21 Merge branch 'main' into cherry-pick-storage-refactor 2023-12-30 21:38:58 -08:00
Charles Packer
02a8a42cb0 fix: patch TEI error in load (#725) 
* patch TEI error in load (now get different error)

* more hiding of MOCKLLM

* fix embedding dim

* refactored bandaid patches into custom embedding class return object patch
 2023-12-27 22:09:29 -08:00
Sarah Wooders
5b991988f6 Deprecate list_loaded_data for listing sources, and use metadata DB instead 2023-12-26 18:47:16 +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
Sarah Wooders
11096b20a4 Set get_all limit to None by default and add postgres to archival memory tests 2023-12-26 17:07:54 +04:00
Sarah Wooders
b64f3aca4b Support metadata table via storage connectors for data sources 2023-12-26 17:06:58 +04:00
Sarah Wooders
223e196da8 Support recall and archival memory for postgres 
working test
 2023-12-26 17:05:24 +04:00
Sarah Wooders
408df89c9c Add in memory storage connector implementation for refactored storage 2023-12-26 17:05:24 +04:00
Sarah Wooders
d041455375 Add data_types.py file for standard data types 2023-12-26 17:05:12 +04:00
Sarah Wooders
234a444090 Define refactored storage table types (archival, recall, documents, 
users, agents)
 2023-12-26 17:04:11 +04:00
Charles Packer
3ec8bb1465 fix: misc fixes (#700) 
* add folder generation

* disable default temp until more testing is done

* apply embedding payload patch to search, add input checking for better runtime error messages

* streamlined memory pressure warning now that heartbeats get forced
 2023-12-25 01:29:13 -08:00
Charles Packer
34e36ad8ef moved configs for hosted to https, patched bug in embedding creation (#685) 2023-12-23 11:40:07 -08:00
Charles Packer
4f23934e04 feat: Add new wrapper defaults (#656) 2023-12-21 17:05:38 +04:00
Charles Packer
52d4befdba fix runtime error (#586) 2023-12-05 23:01:37 -08:00
Sarah Wooders
6a155dfc90 Chroma storage integration (#285) 2023-12-05 17:49:00 -08:00
Sarah Wooders
2d23370930 Removing dead code + legacy commands (#536) 2023-11-30 13:37:11 -08:00
Sarah Wooders
b05b09439f Add user field for vLLM endpoint (#531) 2023-11-29 12:30:42 -08:00
Charles Packer
f4a1455c24 Clean memory error messages (#523) 
* Raise a custom keyerror instead of basic keyerror to clarify issue to LLM processor

* remove self value from error message passed to LLM processor

* simplify error message propogated to llm processor
 2023-11-27 16:41:42 -08:00
Sarah Wooders
ed356dd82c Add support for HuggingFace Text Embedding Inference endpoint for embeddings (#524) 2023-11-27 16:28:49 -08:00
Charles Packer
04e6d548c3 extra arg being passed causing a runtime error (#517) 2023-11-27 11:36:26 -08:00
Charles Packer
9989fd9a52 Fix #487 (summarize call uses OpenAI even with local LLM config) (#488) 
* use new chatcompletion function that takes agent config inside of summarize

* patch issue with model now missing
 2023-11-19 14:54:12 -08:00
sahusiddharth
351f8094b5 Docs: Fix typos (#477) 2023-11-17 15:12:14 -08:00
Charles Packer
624650c13d patch #428 (#433) 2023-11-12 22:59:53 -08:00
Charles Packer
dab47001a9 Fix max tokens constant (#374) 
* stripped LLM_MAX_TOKENS constant, instead it's a dictionary, and context_window is set via the config (defaults to 8k)

* pass context window in the calls to local llm APIs

* safety check

* remove dead imports

* context_length -> context_window

* add default for agent.load

* in configure, ask for the model context window if not specified via dictionary

* fix default, also make message about OPENAI_API_BASE missing more informative

* make openai default embedding if openai is default llm

* make openai on top of list

* typo

* also make local the default for embeddings if you're using localllm instead of the locallm endpoint

* provide --context_window flag to memgpt run

* fix runtime error

* stray comments

* stray comment
 2023-11-09 17:59:03 -08:00
Vivian Fang
11326ec24e Remove AsyncAgent and async from cli (#400) 
* Remove AsyncAgent and async from cli

Refactor agent.py memory.py

Refactor interface.py

Refactor main.py

Refactor openai_tools.py

Refactor cli/cli.py

stray asyncs

save

make legacy embeddings not use async

Refactor presets

Remove deleted function from import

* remove stray prints

* typo

* another stray print

* patch test

---------

Co-authored-by: cpacker <packercharles@gmail.com>
 2023-11-09 14:51:12 -08:00
Sarah Wooders
cef4d8489d Add support for larger archival memory stores (#359) 2023-11-09 09:09:57 -08:00
Sarah Wooders
fb29290dd4 Dependency management (#337) 
* Divides dependencies into `pip install pymemgpt[legacy,local,postgres,dev]`. 
* Update docs
 2023-11-06 19:45:44 -08:00
Charles Packer
caba2f468c Create docs pages (#328) 
* Create docs  (#323)

* Create .readthedocs.yaml

* Update mkdocs.yml

* update

* revise

* syntax

* syntax

* syntax

* syntax

* revise

* revise

* spacing

* Docs (#327)

* add stuff

* patch homepage

* more docs

* updated

* updated

* refresh

* refresh

* refresh

* update

* refresh

* refresh

* refresh

* refresh

* missing file

* refresh

* refresh

* refresh

* refresh

* fix black

* refresh

* refresh

* refresh

* refresh

* add readme for just the docs

* Update README.md

* add more data loading docs

* cleanup data sources

* refresh

* revised

* add search

* make prettier

* revised

* updated

* refresh

* favi

* updated

---------

Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
 2023-11-06 12:38:49 -08:00
Charles Packer
cc1ce0ce33 Remove embeddings as argument in archival_memory.insert (#284) 2023-11-05 12:48:22 -08:00
Vivian Fang
1871823c99 hotfix DummyArchivalMemoryWithFaiss 2023-11-03 16:41:06 -07:00
Sarah Wooders
b9ce763fda VectorDB support (pgvector) for archival memory (#226) 2023-11-03 16:19:15 -07:00
Charles Packer
25dd225d04 strip '/' and use osp.join (Windows support) (#283) 
* strip '/' and use osp.join

* grepped for MEMGPT_DIR, found more places to replace '/'

* typo

* grep pass over filesep

---------

Co-authored-by: Vivian Fang <hi@vivi.sh>
 2023-11-03 13:54:29 -07:00