Fimeg/letta-server
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity
3,426 Commits 1 Branch 0 Tags
ae7d08b2f594483f0694dea136bb69ed4ff78e52
Commit Graph

3426 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
cpacker
92be6d1ff9 changed alt system naming 2023-10-31 12:21:28 -07:00
tractorjuice
449df7eeec Create memgpt_chat_spr.txt (#158) 
This version of the prompt compressed using SPR seems to work well, but needs more testing.
 2023-10-31 12:18:39 -07:00
sk
9fa75e1752 Added db load ability (#106) 
* Added db load ability, updated README

* Fixed spacing on multiplication

* Fixed double quotes

* Added double quotes to .db

* After reading the code, realized we can return here for .db extension, and let main handle loading the .db into archival memory.
Issue is that the final else was treating the db as a file and reading it in raw, causing issues.

* Removed .csv reference, not currently working.
 2023-10-31 12:18:12 -07:00
Web 3 Wes
e9e5d341a6 update max new tokens (#182) 
Co-authored-by: Clarence Jones <wes@Clarences-MacBook-Pro.local>
 2023-10-31 12:16:11 -07:00
Vivian Fang
d6c3f0ea0f Gracefully catch errors when running agent.step() (#216) 
* Gracefully catch errors when running agent.step()

* Modify retry message
 2023-10-31 12:12:07 -07:00
Charles Packer
4e440404ff patch bug (#221) 2023-10-31 11:43:38 -07:00
Vivian Fang
d00032d1d1 Bump version to 0.1.15 2023-10-31 00:35:42 -07:00
Vivian Fang
0ac2ac10db Fix conversation_date_search async bug (#215) 
* Fix conversation_date_search async bug

* Also catch TypeError
 2023-10-31 00:35:09 -07:00
Vivian Fang
446c45e9a9 Bump version to 0.1.14 2023-10-30 23:44:47 -07:00
raisindetre
12ca6e98af Changes to lmstudio to fix JSON decode error (#208) 
* Changes to lmstudio to fix JSON decode error

* black formatting

* properly handle context overflow error (propogate exception up the stack with recognizable error message) + add backwards compat option to use completions endpoint

* set max tokens to 8k, comment out the overflow policy (use memgpt's overflow policy)

* 8k not 3k

---------

Co-authored-by: Matt Poff <mattpoff@Matts-MacBook-Pro-2.local>
Co-authored-by: cpacker <packercharles@gmail.com>
 2023-10-30 23:08:00 -07:00
Vivian Fang
6f4e280432 Bump version to 0.1.13 2023-10-30 21:34:09 -07:00
Vivian Fang
c50c00132b initialize memgpt agent config with same name passed in (#211) 2023-10-30 21:33:27 -07:00
Vivian Fang
2a54511e52 hotfix LocalArchivalMemory (#209) 2023-10-30 20:37:33 -07:00
Vivian Fang
6c6ce2ca2d Bump version to 0.1.12 2023-10-30 18:19:27 -07:00
Vivian Fang
2734890da3 Refactor autogen agent to use sync memgpt, add notebook example (#157) 
* Refactor autogen agent to use sync memgpt, add notebook example

* Add colab badge to notebook

* Update colab badge to point to main

* Add imports lost in the merge

* Changes to make autogenagent work with cli refactor
 2023-10-30 18:09:51 -07:00
Sarah Wooders
8ab04772ec Update requirements.txt with prettytable 2023-10-30 18:04:26 -07:00
Charles Packer
7fe659834c Update agent_groupchat.py 2023-10-30 17:32:19 -07:00
Sarah Wooders
23f3d42fae Refactoring CLI to use config file, connect to Llama Index data sources, and allow for multiple agents (#154) 
* Migrate to `memgpt run` and `memgpt configure` 
* Add Llama index data sources via `memgpt load` 
* Save config files for defaults and agents
 2023-10-30 16:47:54 -07:00
Vivian Fang
5a6b0ef1e8 Hotfix bug from async refactor (#203) 2023-10-30 15:38:25 -07:00
Charles Packer
cc84d46d8b added more clear warnings for when HOST and HOST_TYPE are not set (#202) 2023-10-30 14:14:52 -07:00
Vivian Fang
8b86fc8f8e Fix persona selection for local LLM, bump version 2023-10-30 02:10:26 -07:00
Vivian Fang
864b416ebf Bump version 2023-10-29 22:44:40 -07:00
Vivian Fang
e7caf22f49 Fix summarizer bug in async agent (#195) 2023-10-29 22:43:17 -07:00
tractorjuice
fcbf21419f Update agent.py (#185) 
Fix missing bracket in construct_system_with_memory
 2023-10-29 21:46:23 -07:00
Charles Packer
e47336ed48 black format patch for zephyr pr 2023-10-29 21:34:32 -07:00
Kamelowy
11d576f7e6 New wrapper for Zephyr models + little fix in memory.py (#183) 
* VectorIndex -> VectorStoreIndex

VectorStoreIndex is imported but non-existent VectorIndex is used.

* New wrapper for Zephyr family of models.

With inner thoughts.

* Update chat_completion_proxy.py for Zephyr Wrapper
 2023-10-29 21:17:01 -07:00
Charles Packer
819028d136 azure typo patch (#192) 
* azure typo patch

* Make azure embeddings var consistent

---------

Co-authored-by: Vivian Fang <hi@vivi.sh>
 2023-10-29 21:04:49 -07:00
Wes
4f96810a90 Allow recursive blobs (#186) 
* Allow recursive blobs in file utils.

* Make recursive blobs default behavior.
 2023-10-29 21:01:57 -07:00
Charles Packer
06871cc298 black patch on outstanding files that were causing workflow fails on PRs (#193) 2023-10-29 20:53:46 -07:00
Ajay Gonepuri (GONAPCORP)
1b168a3168 Fix typos (#172) 
* Update memgpt_gpt35_extralong.txt
 2023-10-29 11:15:16 -07:00
Charles Packer
60aa871f02 Create black_format.yml 2023-10-28 22:39:35 -07:00
Charles Packer
139f06f091 use urljoin instead of path.join (#173) 2023-10-28 20:41:44 -07:00
Charles Packer
a9a6a2629a hotfix for broken sync agent code (#171) 2023-10-28 20:15:55 -07:00
Charles Packer
938ba8dcc5 Update README.md 2023-10-28 19:42:23 -07:00
Charles Packer
6de682a187 Update README.md 2023-10-28 18:37:26 -07:00
Mahmoud Almontasser
992c281a62 add missing pip requirement llama_index (#166) 2023-10-28 18:36:37 -07:00
Vivian Fang
0c1cf4bb31 Bump version 2023-10-28 18:34:24 -07:00
Charles Packer
78cb676cd2 LM Studio inference server support (#167) 
* updated airo wrapper to catch specific case where extra closing } is missing

* added lmstudio support
 2023-10-28 18:30:35 -07:00
Charles Packer
d206de5687 Update README.md 2023-10-28 18:27:16 -07:00
Charles Packer
7194e98669 Update README.md 2023-10-28 18:26:42 -07:00
Vivian Fang
53cacad075 Add synchronous memgpt agent (#156) 2023-10-27 16:48:14 -07:00
Sarah Wooders
afdc79e4bd Merge pull request #146 from sarahwooders/main 
Support loading data into archival with Llama Index connectors
 2023-10-27 13:28:26 -07:00
Vivian Fang
07b5d32316 hotfix 2023-10-27 13:22:36 -07:00
Vivian Fang
2b48b259c9 Default to no when prompting user for preloading into archival memory 2023-10-27 13:20:09 -07:00
Charles Packer
3cab8c19a1 Merge pull request #126 from QZGao/main 
Integration with AutoGen workflow
 2023-10-27 12:33:34 -07:00
Charles Packer
0f27c1a57a Updated README.md with Poetry install instructions 2023-10-27 12:14:42 -07:00
Qingzheng Gao
5227b477f4 Set example to True 2023-10-27 13:57:01 +08:00
Qingzheng Gao
8ac3fbcde0 Merge newest fix 2023-10-27 13:56:08 +08:00
Qingzheng Gao
b2fcbd0241 add examples 2023-10-27 13:52:50 +08:00
Sarah Wooders
7df12096d0 update poetry 2023-10-26 17:43:37 -07:00