Commit Graph

3967 Commits

Author SHA1 Message Date
MSZ-MGS
197d46c66a Update lmstudio.md to show the Prompt Formatting Option (#384)
* Update lmstudio.md to show the Prompt Formatting Option

* Update lmstudio.md Update the screenshot
2023-11-08 12:34:45 -08:00
Charles Packer
4fca38a56d Update lmstudio.md (#382)
* Update lmstudio.md

* Update lmstudio.md
2023-11-08 11:54:56 -08:00
Vivian Fang
1378e5ed5e Add pymemgpt-nightly workflow (#373)
* Add pymemgpt-nightly workflow

* change token name
2023-11-07 23:09:59 -08:00
Charles Packer
6768c1a4e1 Create pull_request_template.md (#368)
* Create pull_request_template.md
2023-11-07 17:52:45 -08:00
Charles Packer
29d67ba848 Updated documentation for users (#365)
---------

Co-authored-by: Vivian Fang <hi@vivi.sh>
2023-11-07 17:30:14 -08:00
Charles Packer
267697e98e disable pretty exceptions (#367) 2023-11-07 17:27:31 -08:00
Sarah Wooders
a733203bce Remove requirements.txt and requirements_local.txt (#358)
* update requirements to match poetry

* update with extras

* remove requirements
2023-11-07 17:26:11 -08:00
Vivian Fang
a66d05ba9d Bump version to 0.1.18 (#351) 2023-11-06 22:07:18 -08:00
Vivian Fang
5b8812c822 Revert relaxing verify_first_message_correctness, still add archival_memory_search as an exception (#350)
* Revert "Relax verify_first_message_correctness to accept any function call (#340)"

This reverts commit 30e911057d755f5946d7bc2ba54619b5f2e08dc3.

* add archival_memory_search as an exception for verify
2023-11-06 22:00:40 -08:00
Charles Packer
a4e9240316 add gpt-4-turbo (#349)
* add gpt-4-turbo

* add in another place

* change to 3.5 16k
2023-11-06 21:53:49 -08:00
Vivian Fang
1942ecee76 Add autogen example that lets you chat with docs (#342)
* Relax verify_first_message_correctness to accept any function call

* Also allow missing internal monologue if request_heartbeat

* Cleanup

* get instead of raw dict access

* Support attach in memgpt autogen agent

* Add docs example

* Add documentation, cleanup
2023-11-06 21:06:13 -08:00
Sarah Wooders
4fed48f75c Update poetry.lock (#346)
* mark depricated API section

* add readme

* add readme

* add readme

* add readme

* add readme

* add readme

* add readme

* add readme

* add readme

* CLI bug fixes for azure

* check azure before running

* Update README.md

* Update README.md

* bug fix with persona loading

* remove print

* make errors for cli flags more clear

* format

* fix imports

* fix imports

* add prints

* update lock
2023-11-06 21:02:56 -08:00
Vivian Fang
86f500d513 Relax verify_first_message_correctness to accept any function call (#340)
* Relax verify_first_message_correctness to accept any function call

* Also allow missing internal monologue if request_heartbeat

* Cleanup

* get instead of raw dict access
2023-11-06 20:53:40 -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
Sarah Wooders
3f61969cc2 Avoid throwing error for older ~/.memgpt/config files due to missing section archival_storage (#344)
* avoid error if has old config type
2023-11-06 18:49:49 -08:00
Sarah Wooders
e07a7ac1ef Fix config tests (#343)
Co-authored-by: Vivian Fang <hi@vivi.sh>
2023-11-06 18:43:23 -08:00
Sarah Wooders
8700158222 Specify model inference and embedding endpoint separately (#286) 2023-11-06 17:19:45 -08:00
Mo Nuaimat
8adef204e6 Fixing some dict value checking for function_call (#249) 2023-11-06 15:44:51 -08:00
Vivian Fang
87fc69baae Better error message printing for function call failing (#291)
* Better error message printing for function call failing

* only one import traceback

* don't forward entire stack trace to memgpt
2023-11-06 15:32:58 -08:00
Vivian Fang
4edba17419 Better interface output for function calls (#296)
Co-authored-by: Charles Packer <packercharles@gmail.com>
2023-11-06 15:21:30 -08:00
Charles Packer
fe2d8b2b2f add ollama support (#314)
* untested

* patch

* updated

* clarified using tags in docs

* tested ollama, working

* fixed template issue by creating dummy template, also added missing context length indicator

* moved count_tokens to utils.py

* clean
2023-11-06 15:11:22 -08:00
Sarah Wooders
cb12f7043b Add memgpt version command and package version (#336) 2023-11-06 13:38:50 -08:00
Sarah Wooders
d9f435b405 Update quickstart.md to show flag list properly 2023-11-06 13:09:38 -08:00
Vivian Fang
733ad56a91 Add autogen+localllm docs (#335)
Co-authored-by: Jirito0 <jirito0@users.noreply.github.com>
2023-11-06 13:08:12 -08:00
Sarah Wooders
6217234942 Fix README local LLM link 2023-11-06 13:05:24 -08:00
Sarah Wooders
1595897fb8 Remove redundant docs from README (#334) 2023-11-06 13:01:32 -08:00
Hans Raaf
a9e91e120f Stopping the app to repeat the user message in normal use. (#304)
- Removed repeating every user message like bein in debug mode
- Re-added the "dump" flag for the user message, to make it look nicer.
  I may "reformat" other message too when dumping, but that was what
  sticked out to me as unpleasant.
2023-11-06 12:58:28 -08:00
Charles Packer
5ac8635446 cleanup #326 (#333) 2023-11-06 12:57:19 -08:00
borewik
dbbb3fc14b Update chat_completion_proxy.py (#326)
grammar_name Has to be defined, if not there's an issue with line 92
2023-11-06 12:53:17 -08:00
Charles Packer
f5e6497668 patch in-chat command info (#332) 2023-11-06 12:50:27 -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
Sarah Wooders
d9b9ad4860 Fix formatting in README.md 2023-11-05 11:18:38 -08:00
Sarah Wooders
3fd9f1b8e4 Fix: imported wrong storage connector (#320) 2023-11-05 10:19:33 -08:00
Dividor
b65972a1dc Aligned code with README that environment variable for Azure embeddings should be AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT (#308) 2023-11-05 10:01:02 -08:00
Sarah Wooders
d2afc1e86f Don't import postgres storage if not specified in config (#318) 2023-11-05 09:52:18 -08:00
Robin Goetz
ca0ad1ecc1 fix: import PostgresStorageConnector only if postgres is selected as storage type (#310) 2023-11-05 09:49:05 -08:00
Vivian Fang
f18429c416 Bump version to 0.1.18-alpha.1 2023-11-04 12:08:25 -07:00
Charles Packer
e90c00ad63 Add grammar-based sampling (for webui, llamacpp, and koboldcpp) (#293)
* add llamacpp server support

* use gbnf loader

* cleanup and warning about grammar when not using llama.cpp

* added memgpt-specific grammar file

* add grammar support to webui api calls

* black

* typo

* add koboldcpp support

* no more defaulting to webui, should error out instead

* fix grammar

* patch kobold (testing, now working) + cleanup log messages

Co-Authored-By: Drake-AI <drake-ai@users.noreply.github.com>
2023-11-04 12:02:44 -07:00
danx0r
2f56e0eaf5 FIx #261 (#300)
* should fix issue 261 - pickle fail on DotDict class

* black patch

---------

Co-authored-by: cpacker <packercharles@gmail.com>
2023-11-03 23:33:59 -07:00
Charles Packer
2d57564c35 make timezone local by default (#298)
Co-authored-by: orderwat <github@oderwat.de>
2023-11-03 21:15:15 -07:00
Hans Raaf
71d696dc9e I added a "/retry" command to retry for getting another answer. (#188)
* I added a "/retry" command to retry for getting another answer.

- Implemented to pop messages until hitting the last user message. Then
  extracting the users last message and sending it again. This will also
  work with state files and after manually popping messages.
- Updated the README to include /retry
- Update the README for "pop" with parameter and changed default to 3 as
  this will pop "function/assistant/user" which is the usual turn
  around.

* disclaimer

---------

Co-authored-by: Charles Packer <packercharles@gmail.com>
2023-11-03 21:04:37 -07:00
Hans Raaf
dcdfa04fc0 I added commands to shape the conversation: (#218)
* I added commands to shape the conversation:

`/rethink <text>` will change the internal dialog of the last assistant message.
`/rewrite <text>` will change the last answer of the assistant.

Both commands can be used to change how the conversation continues in
some pretty drastic and powerfull ways.

* remove magic numbers

* add disclaimer

---------

Co-authored-by: cpacker <packercharles@gmail.com>
2023-11-03 20:57:43 -07:00
Hans Raaf
9189a7bf26 I made dump showing more messages and added a count (the last x) (#204)
* I made dump showing more message and added a count (the last x)

There seem to be some changes about the implementation so that the
current dump message helper functions do not show a lot of useful info.

I changed it so that you can `dump 5` (last 5 messages) and that it will
print user readable output. This lets you get some more understanding about
what is going on.

As some messages are still not shown I also show the index (reverse) of the
printed message, so one can see what to "pop" to reach a special point
without geting into the drumpraw.

* black

* patch

---------

Co-authored-by: Charles Packer <packercharles@gmail.com>
2023-11-03 20:47:23 -07:00
Charles Packer
94893b4bd5 try to patch hanging test (#295)
* try to patch hanging test

* add a timeout on the test
2023-11-03 19:11:29 -07:00
Vivian Fang
1871823c99 hotfix DummyArchivalMemoryWithFaiss 2023-11-03 16:41:06 -07:00
cpacker
e0ecd43d96 hotfix 2023-11-03 16:25:39 -07:00
Sarah Wooders
b9ce763fda VectorDB support (pgvector) for archival memory (#226) 2023-11-03 16:19:15 -07:00
Sarah Wooders
c1fd8d6df1 Make CLI agent flag errors more clear, and dont throw error if flags dont contradict existing agent config (#290) 2023-11-03 14:13:44 -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