Charles Packer
9fc4dedd7b
Update autogen.md
2023-12-01 11:36:01 -08:00
Charles Packer
69668d275b
Update ollama.md
2023-12-01 11:33:18 -08:00
Charles Packer
152f78d3d8
Update ollama.md
2023-12-01 11:32:22 -08:00
Charles Packer
d24f294f2b
Update ollama.md
2023-12-01 11:31:19 -08:00
Charles Packer
a344732ce1
Update vllm.md
2023-12-01 11:29:00 -08:00
Charles Packer
5d3f2f1a12
added vLLM doc page since we support it ( #545 )
...
* added vLLM doc page since we support it
* capitalization
* updated documentation
2023-12-01 11:27:24 -08:00
Charles Packer
a2bf5a2b58
update docs ( #547 )
...
* update admonitions
* Update local_llm.md
* Update webui.md
* Update autogen.md
* Update storage.md
* Update example_chat.md
* Update example_data.md
* Update example_chat.md
* Update example_data.md
2023-12-01 11:23:43 -08:00
Charles Packer
b80b816856
Update autogen.md ( #544 )
2023-11-30 18:12:15 -08:00
Charles Packer
8323fb6ec3
clean docs ( #543 )
2023-11-30 18:09:14 -08:00
Charles Packer
fe7193eea3
Documentation update ( #541 )
...
* Update autogen.md
* Update autogen.md
2023-11-30 17:52:47 -08:00
Charles Packer
e9010068a9
Update local_llm.md ( #542 )
2023-11-30 17:52:32 -08:00
Charles Packer
b741b601fb
Update AutoGen documentation and notebook example ( #540 )
...
* Update AutoGen documentation
* Update webui.md
* Update webui.md
* Update lmstudio.md
* Update lmstudio.md
* Update mkdocs.yml
* Update README.md
* Update README.md
* Update README.md
* Update autogen.md
* Update local_llm.md
* Update local_llm.md
* Update autogen.md
* Update autogen.md
* Update autogen.md
* refreshed the autogen examples + notebook (notebook is untested)
* unrelated patch of typo I noticed
* poetry remove pyautogen, then manually removed autogen extra in .toml
* add pdf dependency
---------
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com >
2023-11-30 17:45:04 -08:00
Sarah Wooders
2857ae1c81
Remove usage of BACKEND_TYPE ( #539 )
2023-11-30 14:18:25 -08:00
Sarah Wooders
2d23370930
Removing dead code + legacy commands ( #536 )
2023-11-30 13:37:11 -08:00
Sarah Wooders
313dc471c8
Run formatting checks with poetry ( #537 )
...
* update black version
* add workflow dispatch
2023-11-30 13:30:58 -08:00
Charles Packer
0b5d921843
Update contributing.md (typo) ( #538 )
2023-11-30 13:29:28 -08:00
Charles Packer
5e7676e133
Remove openai package and migrate to requests ( #534 )
2023-11-30 13:00:13 -08:00
Ayush Chaurasia
4a2a28981b
LanceDB integration bug fixes and improvements ( #528 )
...
* fixes
* update
* lint
2023-11-30 10:32:29 -08:00
Charles Packer
8bd29c90ba
Update bug_report.md
2023-11-29 13:32:20 -08:00
Charles Packer
0621fc6934
Update bug_report.md ( #532 )
2023-11-29 13:29:41 -08:00
Charles Packer
a367ee4072
patched a bug where outputs of a regex extraction weren't getting cast back to string, causing an issue when the dict was then passed to json.dumps() ( #533 )
2023-11-29 12:57:05 -08:00
Sarah Wooders
b05b09439f
Add user field for vLLM endpoint ( #531 )
2023-11-29 12:30:42 -08:00
Sarah Wooders
eca26be7ea
add autogen extra ( #530 )
2023-11-29 11:30:27 -08:00
Claudio Cambra
2ec6c512c4
Fix class names used in persistence manager logging ( #503 )
...
* Fix class names used in persistence manager logging
Signed-off-by: Claudio Cambra <developer@claudiocambra.com >
* Use self.__class__.__name__ for logging in different persistence managers
Signed-off-by: Claudio Cambra <developer@claudiocambra.com >
---------
Signed-off-by: Claudio Cambra <developer@claudiocambra.com >
2023-11-28 23:11:11 -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
Charles Packer
c5d04ede82
Update mkdocs.yml ( #525 )
2023-11-27 16:35:20 -08:00
Charles Packer
89013567fa
Update mkdocs theme, small fixes for mkdocs.yml ( #522 )
2023-11-27 16:30:41 -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
3bc20291b4
Update contributing.md ( #520 )
2023-11-27 13:51:30 -08:00
Charles Packer
1a490b8aef
Update contributing.md ( #518 )
2023-11-27 13:05:30 -08:00
Sarah Wooders
bd4eeb3ccd
Update contributing guidelines ( #516 )
...
* update contributing
* Update CONTRIBUTING.md
* Update CONTRIBUTING.md
* Update CONTRIBUTING.md
* Update CONTRIBUTING.md
* Update CONTRIBUTING.md
2023-11-27 13:01:47 -08:00
Paul Asquin
20fe8ddc92
fix autogem to autogen ( #512 )
2023-11-27 13:00:33 -08:00
Sarah Wooders
fe6be5c3bd
Add warning if no data sources loaded on /attach command ( #513 )
...
* minor fix
* add warn instead of error for no data sources
2023-11-27 13:00:23 -08:00
Charles Packer
04e6d548c3
extra arg being passed causing a runtime error ( #517 )
2023-11-27 11:36:26 -08:00
Charles Packer
188236b457
add core memory char limits to text shown in core memory ( #508 )
...
* add core memory char limits to text shown in core memory
* include char limit in xml tag
* add flag to allow reverting to old version
2023-11-26 20:00:01 -08:00
Charles Packer
f92d8dfc8b
add a longer prefix that to the default wrapper ( #510 )
...
* add a longer prefix that to the default wrapper (not just opening brace, but up to 'function: ' part since that is always present)
* drop print
2023-11-26 19:59:49 -08:00
Charles Packer
2121130a88
add new manual json parser meant to catch send_message calls with trailing bad extra chars ( #509 )
...
* add new manual json parser meant to catch send_message calls with stray trailing chars, patch json error passing
* typo
2023-11-25 16:30:12 -08:00
Sarah Wooders
58bdb1ebd0
update version ( #497 )
2023-11-22 08:58:24 -08:00
Charles Packer
7712a06ffd
Fixes bugs with AutoGen implementation and exampes ( #498 )
...
* patched bugs in autogen agent example, updated autogen agent creation to follow agentconfig paradigm
* more fixes
* black
* fix bug in autoreply
* black
* pass default autoreply through to the memgpt autogen conversibleagent subclass so that it doesn't leave empty messages which can trigger errors in local llm backends like lmstudio
2023-11-21 19:15:28 -08:00
Charles Packer
823a3e1694
Add error handling during linking imports ( #495 )
...
* Add error handling during linking imports
* correct typo + make error message even more explicit
* deadcode
2023-11-21 15:16:16 -08:00
Charles Packer
de0ccea181
vLLM support ( #492 )
...
* init vllm (not tested), uses POST API not openai wrapper
* add to cli config list
* working vllm endpoint
* add model configuration for vllm
---------
Co-authored-by: Sarah Wooders <sarahwooders@gmail.com >
2023-11-21 15:16:03 -08:00
Max Blackmer, CSM
d72edb6a99
ANNA, an acronym for Adaptive Neural Network Assistant. Which acts as your personal research assistant really good with archival documents and research. ( #494 )
2023-11-20 11:43:08 -08:00
Charles Packer
8a7a64c7f9
patch web UI ( #484 )
...
* patch web UI
* set truncation_length
2023-11-19 14:56:10 -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
Charles Packer
4ba4c02fa1
Remove .DS_Store from agents list ( #485 )
2023-11-19 14:35:51 -08:00
sahusiddharth
351f8094b5
Docs: Fix typos ( #477 )
2023-11-17 15:12:14 -08:00
Prashant Dixit
11e11bfac4
Lancedb storage integration ( #455 )
2023-11-17 11:36:30 -08:00
Charles Packer
86ac4ff4de
updated websocket protocol and server ( #473 )
2023-11-16 22:50:00 -08:00
Charles Packer
576795ffdb
move webui to new openai completions endpoint, but also provide existing functionality via webui-legacy backend ( #468 )
2023-11-15 23:08:30 -08:00
Charles Packer
398287d1ca
Add d20 function example to readthedocs ( #464 )
...
* Update functions.md
* Update functions.md
2023-11-15 16:12:16 -08:00
