Fimeg/letta-server
1
0
Fork 0
Code Issues 4 Pull Requests Actions 3 Packages Projects Releases Wiki Activity
1,070 Commits 1 Branch 0 Tags
a80b7e8fecdb97a17cbf720fbda7a27dbbeefdf7
Commit Graph

85 Commits

Author SHA1 Message Date
Charles Packer
b35de11d96 chore: run autoflake + isort (#1279) 2024-04-20 11:40:22 -07:00
Charles Packer
d7d1bd1516 feat: add streaming support for OpenAI-compatible endpoints (#1262) 2024-04-17 23:40:52 -07:00
Charles Packer
703ea47d72 feat: add Google AI Gemini Pro support (#1209) 2024-04-10 19:43:44 -07:00
Sarah Wooders
806a982b39 feat: REST API support for tool creation (#1219) 
Co-authored-by: cpacker <packercharles@gmail.com>
 2024-04-08 22:11:18 -07:00
Charles Packer
4b5666ac64 fix: patch out-of-sync / missing tzinfo timestamps coming back from API server (#1182) 2024-03-26 20:37:44 -07:00
Charles Packer
6d62141384 feat: migrate all calls to datetime.now() to datetime.now(UTC) (#1176) 2024-03-21 12:36:56 -07:00
Charles Packer
16a9bddb22 fix: (1) refactor in Agent.step() to fix out-of-order timestamps, (2) bug fixes with usage of preset/human vs filename values (#1145) 2024-03-16 20:11:31 -07:00
Charles Packer
1f192be107 feat: added persona/human_name fields to Preset (#1134) 2024-03-11 16:33:05 -07:00
Charles Packer
fe4a3f75b8 fix: small typing fixes (#1123) 2024-03-10 15:40:45 -07:00
Charles Packer
d984daa3c4 feat: pass message UUIDs during message streaming (POST SSE send_message) (#1120) 2024-03-10 15:34:37 -07:00
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
b665e67b01 feat: isolate test config from main config (#1063) 
Co-authored-by: Charles Packer <packercharles@gmail.com>
 2024-03-05 16:21:37 -08:00
Charles Packer
e7f42d1420 fix: patch AutoGen integration for 0.3.5 + add AutoGen integration tests (#1081) 2024-03-02 13:45:12 -08:00
Charles Packer
894cfcb0c5 feat: tests and bug fixes AgentState.state (#1058) 2024-02-29 20:51:31 -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
bf252b90f0 feat: Partial support for OpenAI-compatible assistant API (#838) 2024-02-13 16:09:20 -08:00
Charles Packer
decea1e18f fix: allow multiple tools to be called by LLM and rewrite request (#992) 2024-02-11 18:47:55 -08:00
tombedor
c8e8557c27 fix: set json loads strict to false (#946) 2024-01-31 15:50:08 -08:00
tombedor
ff692fe7ab fix: remove unused param in agent instantiation (#938) 2024-01-29 17:37:59 -08:00
Charles Packer
8b52b26c7d fix: patch tool_call bug in summarizer (#935) 2024-01-27 17:07:45 -08:00
Charles Packer
037cc16e32 refactor: fix typing errors (pyright) (#855) 2024-01-23 17:21:44 -08:00
Charles Packer
b425ec2c80 fix: out-of-order user message timestamp (#915) 2024-01-23 15:42:53 -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
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
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
Maximilian Winter
0c787a11e0 feat: Added grammar generator for function calling. (#796) 
Co-authored-by: Charles Packer <packercharles@gmail.com>
 2024-01-16 15:34:04 -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
ifsheldon
dd2f4fc873 fix: Turn off all ensure_ascii of json.dumps (#800) 2024-01-11 23:54:35 -08:00
Charles Packer
f045c3515c feat: add_function and remove_function commands (#784) 2024-01-10 23:19:14 -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
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
Charles Packer
97e8961528 fix: Update message schema / data type to match OAI tools style (#783) 
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
 2024-01-04 15:05:43 -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
Sarah Wooders
77e72d18da Merge branch 'main' into cherry-pick-storage-refactor 2023-12-27 13:47:27 +04:00
Charles Packer
42e2a301eb fix: increase the func return char limit (#714) 
* increase the funct return limit

* disable truncation for base search functions

* added stdout suppression to remove MockLLM warning
 2023-12-27 01:33:30 -08:00
Sarah Wooders
3f8b9063a1 Run black formatter 2023-12-26 17:53:57 +04:00
Sarah Wooders
b64f3aca4b Support metadata table via storage connectors for data sources 2023-12-26 17:06:58 +04:00
Sarah Wooders
deb7f3c1e1 Enable loading local agents with refactored recall memory + update MemGPTConfig to default to sqlite + chroma 2023-12-26 17:06:56 +04:00
Sarah Wooders
8a3681297a Cleanup agent function linking 2023-12-26 17:05:26 +04:00
Sarah Wooders
223e196da8 Support recall and archival memory for postgres 
working test
 2023-12-26 17:05:24 +04:00
Charles Packer
4f23934e04 feat: Add new wrapper defaults (#656) 2023-12-21 17:05:38 +04:00
Charles Packer
27eb05e7e8 Add safeguard on tokens returned by functions (#576) 
* swapping out hardcoded str for prefix (forgot to include in #569)

* add extra failout when the summarizer tries to run on a single message

* added function response validation code, currently will truncate responses based on character count

* added return type hints (functions/tools should either return strings or None)

* discuss function output length in custom function section

* made the truncation more informative
 2023-12-13 21:57:50 -08:00
Charles Packer
0d8b95e2a7 AutoGen misc fixes (#603) 
* don't add anything except for assistant messages to the global autogen message historoy

* properly format autogen messages when using local llms (allow naming to get passed through to the prompt formatter)

* add extra handling of autogen's name field in step()

* comments
 2023-12-10 20:52:21 -08:00
Charles Packer
f2a2942c66 sort agents by directory-last-modified time (#574) 
* sort agents by directory-last-modified time

* only save agent config when agent is saved

---------

Co-authored-by: Sarah Wooders <sarahwooders@gmail.com>
 2023-12-04 14:16:03 -08:00
Claudio Cambra
14fbfa1406 Fix crash from bad key access into response_message without function_call (#437) 
Signed-off-by: Claudio Cambra <developer@claudiocambra.com>
 2023-12-04 13:58:36 -08:00
Charles Packer
df999de4c1 use a consistent warning prefix across codebase (#569) 2023-12-04 11:38:51 -08:00