Sarah Wooders
c7fbc03e68
refactor: store presets in database via metadata store ( #1013 )
2024-02-15 18:49:16 -08:00
Charles Packer
3546f9df36
fix: various patches for Azure support + strip Box ( #982 )
2024-02-09 15:01:57 -08:00
Charles Packer
6edffe036e
fix: use utf-8 encodings for all text files ( #918 )
2024-01-30 11:59:58 -08:00
Charles Packer
7ec216d1f8
refactor: fix typing errors (pyright) ( #855 )
2024-01-23 17:21:44 -08:00
Robin Goetz
988808e4b6
fix: remove unexpected arguments for user ( #910 )
...
Co-authored-by: Charles Packer <packercharles@gmail.com>
2024-01-23 11:32:33 -08:00
Sarah Wooders
46675f4d41
fix: add Annotated to CLI options ( #906 )
...
Co-authored-by: Charles Packer <packercharles@gmail.com>
2024-01-23 11:27:24 -08:00
Sarah Wooders
cca9b38294
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
7c99fbd009
feat: local auth config ( #854 )
2024-01-18 16:43:41 -08:00
Charles Packer
e4fab1653e
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
Charles Packer
d1b1548ba0
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
tombedor
302e699c11
fix: store opeani key ( #806 )
2024-01-11 20:25:24 -08:00
Charles Packer
75467c2fb8
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
6710f18c07
Merge branch 'main' into feature/global-logging
...
# Conflicts:
# memgpt/config.py
2024-01-11 11:12:03 -05:00
Sarah Wooders
2129212d0a
Fix CLI formatting
2024-01-08 16:58:59 -08:00
Sarah Wooders
8952e07279
Clear out archival and recall memory stores on agent deletion
2024-01-08 16:55:00 -08:00
Sarah Wooders
ca82b33ba7
Add support for deleting sources
2024-01-08 16:49:04 -08:00
Sarah Wooders
8c06cc4bf7
refactor!: Migrate users + agent information into storage connectors ( #785 )
...
Co-authored-by: cpacker <packercharles@gmail.com>
2024-01-08 15:59:49 -08:00
Max Blackmer
2343851cae
Merge branch 'feature/global-logging' of github.com:agiletechnologist/MemGPT into feature/global-logging
...
Removed Logging from configurations and migrated to constants.py
Modified log.py to configure using constants to configure logging
Conflicts:
memgpt/config.py resolved
2024-01-05 18:11:17 -05:00
cpacker
69849ba8e5
added success and fail messages to memgpt source delete
2024-01-02 13:39:26 -08:00
cpacker
bad6abc2f4
don't allow bad endpoint addresses during memgpt configure
2024-01-02 13:27:19 -08:00
cpacker
cdef0729b8
Merge branch 'main' into cherry-pick-storage-refactor
2024-01-02 12:21:56 -08:00
Jim Lloyd
3e5320c87e
feat: enum choices for list command argument (issue #732 ) ( #746 )
...
* enum choices for list command argument
* fixup! enum choices for list command argument
2023-12-31 13:27:10 -08:00
Sarah Wooders
d6aa519202
Update memgpt configure to reflect current storage connector options
2023-12-26 19:28:13 +04:00
Sarah Wooders
83c930e9ce
Deprecate list_loaded_data for listing sources, and use metadata DB instead
2023-12-26 18:47:16 +04:00
Sarah Wooders
887d9e4946
Support data source deletion with 'memgpt delete source <name>'
2023-12-26 18:28:53 +04:00
Max Blackmer
42c73137c9
[cpacker#319] Refactor memgptlog.py to log.py and move a function to log.py
2023-12-26 08:52:24 -05:00
Sarah Wooders
7a304c4df3
Support 'memgpt list sources' for storage refactor
2023-12-26 17:07:18 +04:00
Sarah Wooders
10e956a7be
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
1c018cc14e
Add more compehensive tests, make row ids be strings (not integers)
2023-12-26 17:05:58 +04:00
Sarah Wooders
de88c9d50d
Refactor chroma integration
2023-12-26 17:05:41 +04:00
Sarah Wooders
9b3d59e016
Support recall and archival memory for postgres
...
working test
2023-12-26 17:05:24 +04:00
Max Blackmer, CSM
e67c521da8
Merge branch 'main' into feature/global-logging
2023-12-25 14:53:19 -05:00
Charles Packer
b97064e372
feat: pull model list for openai-compatible endpoints ( #630 )
...
* allow entering custom model name when using openai/azure
* pull models from endpoint
* added/tested vllm and azure
* no print
* make red
* make the endpoint question give you an opportunity to enter your openai api key again in case you made a mitake / want to swap it out
* add cascading workflow for openai+azure model listings
* patched bug w/ azure listing
2023-12-21 23:27:48 -08:00
Charles Packer
09c7fa763b
fix: CLI conveniences (add-on to #674 ) ( #675 )
...
* for openai, check for key and if missing allow user to pass it, for azure, throw error if the key isn't present
* correct prior checking of azure to be more strict, added similar checks at the embedding endpoint config stage
* forgot to override value in config before saving
* clean up the valuerrors from missing keys so that no stacktrace gets printed, make success text green to match others
2023-12-21 21:35:19 -08:00
Matheus
cfbec583ae
fix: Throw "env vars not set" early + enhance attach for KeyboardInterrupt ( #669 ) ( #674 )
2023-12-21 20:47:34 -08:00
Max Blackmer
72f28d3853
[cpacker#319] run Black Reformat on files.
2023-12-19 15:09:08 -05:00
Charles Packer
c0290088db
feat: Migrate docs ( #646 )
...
* updated docs for readme
* Update index.md
* Update index.md
* added header
* broken link
* sync heading sizes
* fix various broken rel links
* Update index.md
* added webp
* Update index.md
* strip mkdocs/rtk files
* replaced readthedocs references with readme
2023-12-18 20:29:24 -08:00
Max Blackmer
f79147b5a6
Merge branch 'feature/global-logging' of github.com:agiletechnologist/MemGPT into feature/global-logging
2023-12-18 16:55:23 -05:00
Max Blackmer
119b1afccd
[ #319 ] Global Logging Configuration with directory fixes at config load.
2023-12-18 16:51:23 -05:00
Charles Packer
5c49265aba
migrate to using completions endpoint by default ( #628 )
...
* migrate to using completions endpoint by default
* added note about version to docs
2023-12-15 12:29:52 -08:00
Charles Packer
b8b375d663
Patch azure embeddings + handle azure deployments properly ( #594 )
...
* Fix bug where embeddings endpoint was getting set to deployment, upgraded pinned llama-index to use new version that has azure endpoint
* updated documentation
* added memgpt example for openai
* change wording to match configure
2023-12-08 16:31:43 -08:00
Sarah Wooders
9c2e6b774c
Chroma storage integration ( #285 )
2023-12-05 17:49:00 -08:00
Charles Packer
ec7fa25c07
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
2adc75d10b
Remove usage of BACKEND_TYPE ( #539 )
2023-11-30 14:18:25 -08:00
Sarah Wooders
dd5a110be4
Removing dead code + legacy commands ( #536 )
2023-11-30 13:37:11 -08:00
Charles Packer
bc0c1e4a37
Remove openai package and migrate to requests ( #534 )
2023-11-30 13:00:13 -08:00
Sarah Wooders
febc7344c7
Add support for HuggingFace Text Embedding Inference endpoint for embeddings ( #524 )
2023-11-27 16:28:49 -08:00
Sarah Wooders
da081667d6
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
2f6ad7878f
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
Prashant Dixit
f957209c35
Lancedb storage integration ( #455 )
2023-11-17 11:36:30 -08:00
