aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2025-12-27 19:04:25 +01:00
Code Issues Packages Projects Releases Wiki Activity
2,141 Commits 1 Branch 0 Tags
71ca4ea9904ecd07a1287fa5b146490be6bd2945
Commit Graph

2141 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Luke
71ca4ea990 Updates to sync 0.4.1 to master 2023-06-19 19:36:46 +00:00
Luke K (pr-0f3t)
eb2410ac6c Merge remote-tracking branch 'upstream/master' into Release-v0.4.1 2023-06-19 14:08:06 -04:00
Auto-GPT-Bot
7d923f83e6 Update cassette submodule 2023-06-19 03:35:37 +00:00
Erik Peterson
9f737274b7 Fix issues with execute_python_code responses (#4738) 
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
 2023-06-18 20:30:08 -07:00
Auto-GPT-Bot
ee7d04775e Update cassette submodule 2023-06-19 03:05:39 +00:00
merwanehamadi
0abfa3a68f Remove config from command decorator (#4736) 2023-06-18 20:00:23 -07:00
Auto-GPT-Bot
8077d2a249 Update cassette submodule 2023-06-19 02:10:07 +00:00
merwanehamadi
a7f805604c Pass config everywhere in order to get rid of singleton (#4666) 
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
 2023-06-18 19:05:41 -07:00
Erik Peterson
096d27f342 Fix execute_command coming from plugins (#4729) 
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
 2023-06-17 14:53:58 -07:00
Erik Peterson
7bac56b57d Fix execute_command coming from plugins (#4730) 2023-06-17 14:45:34 -07:00
Auto-GPT-Bot
dc1b484630 Update cassette submodule 2023-06-17 15:46:07 +00:00
merwanehamadi
10d7747ae2 Use JSON format for commands signature (#4714) 
* Use JSON for command signature

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

* Improve plugin backward compatibility (#4716)

* Fixed plugin test

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

* Fix Docker-CI

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

* Put back commands, clean typing and signatures

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

---------

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Erik Peterson <e@eriklp.com>
Co-authored-by: Luke K (pr-0f3t) <2609441+lc0rp@users.noreply.github.com>
 2023-06-17 08:39:17 -07:00
Luke K (pr-0f3t)
7f6f18f642 Bulletin.md update for 0.4.1 release (#4721) 2023-06-17 04:03:21 -04:00
merwanehamadi
0b6fec4a28 Fix summarization happening in first cycle (#4719) 2023-06-16 18:17:47 -07:00
Luke
4a307ad4eb Fixed plugin test 2023-06-16 11:53:25 +00:00
Luke K (pr-0f3t)
e02105ee89 Improve plugin backward compatibility (#4716) 2023-06-16 08:28:58 -03:00
merwanehamadi
d923004e20 Remove app commands, audio text and playwright (#4711) 
* Remove App Commands and Audio Text
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

* Remove self feedback

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

---------

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Erik Peterson <e@eriklp.com>
 2023-06-15 15:04:51 -07:00
Reinier van der Leer
9943c58fba Fix test_make_agent 2023-06-15 23:59:15 +02:00
Reinier van der Leer
244393e4ef Add fallback token limit in llm.utils.create_chat_completion 2023-06-15 23:11:52 +02:00
merwanehamadi
a30e5a85b2 Remove write_tests command (#4707) 
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Erik Peterson <e@eriklp.com>
 2023-06-15 13:32:20 -07:00
merwanehamadi
512d7ba208 Remove analyze_code (#4705) 
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Erik Peterson <e@eriklp.com>
 2023-06-15 12:55:50 -07:00
Erik Peterson
195a7fcad8 Refactor module layout of command classes (#4706) 2023-06-15 11:34:41 -07:00
Reinier van der Leer
12588b6483 Fix openai.py linting errors 2023-06-15 18:50:26 +02:00
Reinier van der Leer
426cfef882 Unpin OpenAI model versions in model info mapping 2023-06-15 18:19:03 +02:00
merwanehamadi
3525a4b6db Count tokens with tiktoken (#4704) 
* Update OpenAI model info and remove duplicate modelsinfo.py (#4700)

* Update OpenAI model info and remove duplicate modelsinfo.py

* Fix max_tokens for gpt-4-0613

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>

* Update count_message_tokens to support new OpenAI models

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>

* Fix error message in count_message_tokens

---------

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Erik Peterson <e@eriklp.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
 2023-06-15 09:09:59 -07:00
Reinier van der Leer
f0a5250da5 Implement loading MemoryItems from file in JSONFileMemory (#4703) 
Further changes:
* remove `init` param from `get_memory()`, replace usages by `memory.clear()`
* make token length calculation optional in `MemoryItem.dump()`
 2023-06-15 17:45:14 +02:00
Reinier van der Leer
a1e5be7077 Update OpenAI model info and remove duplicate modelsinfo.py (#4700) 
* Update OpenAI model info and remove duplicate modelsinfo.py

* Fix max_tokens for gpt-4-0613
 2023-06-15 08:14:24 -07:00
Reinier van der Leer
bbaa5b89c2 Add CI trigger for release-* branches 2023-06-15 13:16:25 +02:00
James Collins
6e6e7fcc9a Extract openai API calls and retry at lowest level (#3696) 
* Extract open ai api calls and retry at lowest level

* Forgot a test

* Gotta fix my local docker config so I can let pre-commit hooks run, ugh

* fix: merge artiface

* Fix linting

* Update memory.vector.utils

* feat: make sure resp exists

* fix: raise error message if created

* feat: rename file

* fix: partial test fix

* fix: update comments

* fix: linting

* fix: remove broken test

* fix: require a model to exist

* fix: BaseError issue

* fix: runtime error

* Fix mock response in test_make_agent

* add 429 as errors to retry

---------

Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: Nicholas Tindle <nicktindle@outlook.com>
Co-authored-by: Luke K (pr-0f3t) <2609441+lc0rp@users.noreply.github.com>
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>
 2023-06-14 07:59:26 -07:00
Luke K (pr-0f3t)
a5544a06e1 Merge branch 'stable' into Release-v0.4.1 2023-06-14 07:45:58 -03:00
gravelBridge
c17d825bba Remove urls tts macos (#4260) 
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Luke K (pr-0f3t) <2609441+lc0rp@users.noreply.github.com>
 2023-06-14 07:43:06 -03:00
Richard Beales
c76c67a69c Introduce method to ignore unexpected command params (#3570) 
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: Luke K <2609441+lc0rp@users.noreply.github.com>
 2023-06-14 06:03:11 -03:00
Erik Peterson
49d1a5a17b Rework plugin config to be file-based (#4673) 2023-06-13 20:54:55 -07:00
merwanehamadi
0c8f2cfd1c Fix autogpt docker image not working because missing prompt_settings (#4680) 
Co-authored-by: Richard Beales <rich@richbeales.net>
 2023-06-13 20:18:39 +01:00
merwanehamadi
3df8c1b501 Make benchmarks create cassettes without using them (#4664) 2023-06-13 11:29:20 -07:00
Auto-GPT-Bot
857c330d58 Update challenge scores 2023-06-13 16:59:27 +00:00
Erik Peterson
07d9b584f7 Correct and clean up JSON handling (#4655) 
* Correct and clean up JSON handling

* Use ast for message history too

* Lint

* Add comments explaining why we use literal_eval

* Add descriptions to llm_response_format schema

* Parse responses in code blocks

* Be more careful when parsing in code blocks

* Lint
 2023-06-13 09:54:50 -07:00
Kinance
7bf39cbb72 Include the token length of the current summary (#4670) 
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
 2023-06-12 16:29:11 -07:00
Reinier van der Leer
f277e6aa2d Strip spaces from the end of truncated ai_name in log_cycle.py (#4672) 2023-06-12 15:14:15 -07:00
merwanehamadi
d5afbbee26 Add challenge name and level to pytest logs (#4661) 2023-06-12 08:03:14 -07:00
Reinier van der Leer
a9d177eeeb Remove unused function split_file from file_operations.py (#4658) 2023-06-12 02:20:39 +02:00
Kinance
ff46c16805 Remove extra spaces in summarization prompt (#4660) 
* Implement Batch Running Summarization to avoid max token error (#4652)

* Fix extra space in prompt

---------

Co-authored-by: Reinier van der Leer <github@pwuts.nl>
 2023-06-12 02:13:47 +02:00
Reinier van der Leer
62dd1675a0 Add basic Netlify config (#4662) 2023-06-12 02:00:57 +02:00
David
e60dfca9fc Fix run.sh shebang (#4561) 
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
 2023-06-12 01:44:18 +02:00
digger yu
a7faab32fe Fix typo in docs/setup.md (#4613) 
fix typo: depedencies -> dependencies

Co-authored-by: Reinier van der Leer <github@pwuts.nl>
 2023-06-12 01:17:48 +02:00
merwanehamadi
2ce6ae6707 Change memory challenge expectations (#4657) 2023-06-11 14:34:02 -07:00
Erik Peterson
fd04db12fa Use prompt_toolkit to enable keyboard navigation in CLI (#4649) 
* Use prompt_toolkit to enable keyboard navigation in CLI

* Also update other tests

---------

Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
 2023-06-11 14:19:42 -07:00
Kinance
bc5dbb6692 Implement Batch Summarization in MessageHistory Class to manage context length under model's token limit (#4652) 
* Implement Batch Running Summarization to avoid max token error

* Rename test func
 2023-06-11 13:04:41 -07:00
merwanehamadi
9150f32f8b Fix benchmark logs (#4653) 2023-06-11 15:34:57 +01:00
merwanehamadi
6fb9b6d03b Retry regression tests (#4648) 2023-06-11 15:21:26 +01:00