aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2025-12-20 15:34:23 +01:00
Code Issues Packages Projects Releases Wiki Activity
1,302 Commits 1 Branch 0 Tags
147d3733bf068d8c71a901b8a0e31cfda5c4a687
Commit Graph

543 Commits

Author SHA1 Message Date
Maiko Bossuyt
137751f95c Merge branch 'Torantulino:master' into add_ingest_documents_script 2023-04-12 19:36:40 +02:00
Richard Beales
0e004f5c14 Merge pull request #697 from Wladastic/fix-user-feedback-json-error 
fix json parser
 2023-04-12 18:22:47 +01:00
Richard Beales
364e2a4ba1 Merge branch 'master' into add-unit-tests-workflow 2023-04-12 18:14:37 +01:00
Maiko Bossuyt
d7609b3095 Merge branch 'add_ingest_documents_script' of https://github.com/maiko/Auto-GPT into add_ingest_documents_script 2023-04-12 19:13:26 +02:00
Maiko Bossuyt
0dddc94bda Add file ingestion methode in file_operations.py 
Add the following functions to ingest data into memory before Auto-GPT run.

- split_file: given a content, split it in chunks of max_length with (or without) a specified overlap

- ingest_file: read a file, use split_file to split it in chunks and load each chunk in memory

- ingest_directory: ingest all files in a directory in memory
 2023-04-12 19:13:04 +02:00
Richard Beales
9c9758c720 Merge pull request #700 from Rokniel/azure-deployment-additions 
Add required env parameters for azure usage
 2023-04-12 18:08:54 +01:00
Richard Beales
c98471e333 Merge pull request #685 from STRML/fix/json-parsing 
Fix various JSON input bugs
 2023-04-12 18:03:34 +01:00
Bernhard Mueller
940772b502 Merge branch 'shellcommands' of github.com:muellerberndt/Auto-GPT into shellcommands 2023-04-12 23:47:16 +07:00
Bernhard Mueller
affe77e18c Call subprocess.run with shell=True 2023-04-12 23:46:55 +07:00
Richard Beales
a7176cd229 Merge pull request #215 from slavakurilyak/security-and-robustness-improvements 
Improve Security and Robustness in browse.py
 2023-04-12 17:37:44 +01:00
Bernhard Mueller
9e8d35277b Update scripts/commands.py 
Co-authored-by: Peter Stalman <sarkedev@gmail.com>
 2023-04-12 23:32:17 +07:00
Bernhard Mueller
cc9723c26e Make chdir code more robust 2023-04-12 23:30:35 +07:00
Bernhard Mueller
15dffed6e5 Merge branch 'master' of github.com:Torantulino/Auto-GPT into shellcommands 2023-04-12 23:15:31 +07:00
Maiko Bossuyt
8baa0769b1 Update config.py 2023-04-12 18:03:59 +02:00
Maiko Bossuyt
a615e57061 Revert "Update main.py" 
This reverts commit c785352ed2.
 2023-04-12 18:00:17 +02:00
profound
c5f0cb3d3f fix read config file encoding that broke Chinese 2023-04-12 23:38:30 +08:00
roby.parapat
730fbf591f pull image if it's not found locally 2023-04-12 22:15:22 +07:00
Maiko Bossuyt
5bb551db95 add the url variable in the get_text_summary function to pass it to the memory 
By sending the url along when calling browse.summarize_text, we can then add it along the chunk in memory.
 2023-04-12 16:42:14 +02:00
Maiko Bossuyt
b20c0117c5 Add memory management to browse.py 
- Change the way User-Agent is handle when calling requests to browse website

- Add chunk to memory before and after summary. We do not save the "summary of summaries" as this wasn't performing great and caused noise when the "question" couldn't be answered.

- Use the newly added config parameters for max_length and max_token
 2023-04-12 16:38:49 +02:00
Maiko Bossuyt
c986e87135 Edit config Class to manage browse_website command chunk size and summary size 
I added two new config parameters:

- browse_chunk_max_length: define the max_length of a chunk being sent to the memory and to FAST_LLM_MODEL for summarizing

- browse_summary_max_token: define the max_token passed to the model use for summary creation. Changing this can help with complex subject, allowing the agent to be more verbose in its attemps to summarize the chunk and the chunks summary.

I've also edited the way the user_agent is handle.
 2023-04-12 16:36:27 +02:00
Samuel Reed
434f27fb51 Fix various JSON input bugs in correction 
By not having correct_json(json_str) in the try/except,
it was still easily possible to throw Invalid JSON errors.

When responses were received with no JSON at all, parsing
would fail on attempting to locate the braces.
 2023-04-12 10:34:33 -04:00
Alrik Olson
2ef9928a2e Merge remote-tracking branch 'origin/master' into prompt-generator 2023-04-12 07:33:36 -07:00
Maiko Bossuyt
c785352ed2 Update main.py 
clean trailing whitespace
 2023-04-12 16:23:09 +02:00
Eesa Hamza
ec6918ab48 Added some comments 2023-04-12 16:59:50 +03:00
Eesa Hamza
083ccb6bd3 Added a memory backend argument 2023-04-12 16:58:39 +03:00
Wlad
0105dd340a Merge remote-tracking branch 'upstream/master' into fix-user-feedback-json-error 2023-04-12 15:01:24 +02:00
Peter Edwards
6fa9501251 Merge branch 'Torantulino:master' into more_azure 2023-04-12 13:28:23 +02:00
Gull Man
c932087997 add encoding to open file 2023-04-12 12:13:18 +02:00
sarango
16b37fff1d Fix to LocalCache add method, created integration test for it 2023-04-12 21:49:23 +12:00
Peter Edwards
650e2dcd6d cleaned up .env to move Azure config to separate azure.yaml file 
updated README.md to explain new config
added Azure yaml loader to config class
centralized model retrieval into config class
this commit effectively combines and replaces #700 and #580
 2023-04-12 11:27:37 +02:00
Itamar Friedman
1a7159095a Merge remote-tracking branch 'upstream/master' into browse_scrape_links_test_and_validate 2023-04-12 12:18:16 +03:00
Richard Beales
3ea57ca326 Merge pull request #888 from chozzz/bugfix 
Bugfix for #803 - Debug mode
 2023-04-12 10:06:04 +01:00
Wlad
c6605b06c5 Merge remote-tracking branch 'upstream/master' into fix-user-feedback-json-error 2023-04-12 10:58:09 +02:00
Wlad
4063483b87 add my fixes 2023-04-12 10:56:54 +02:00
Richard Beales
4dbf72159d Merge pull request #542 from ccheney/attr-error-lower 
command_name null check before calling .lower()
 2023-04-12 09:54:05 +01:00
Itamar Friedman
e8b7a117da Merge remote-tracking branch 'origin/master' into browse_scrape_links_test_and_validate 2023-04-12 11:51:43 +03:00
Itamar Friedman
98778cea73 Merge remote-tracking branch 'upstream/master' 2023-04-12 11:48:55 +03:00
Richard Beales
a0cebb02db Merge pull request #733 from keenborder786/gpt_4_only_option 
GPT-4 Only Option
 2023-04-12 09:36:45 +01:00
Richard Beales
56ed3eed9b Merge pull request #871 from Legionof7/typofix 
Changed spelling from "GTP" to "GPT". Also removed the 3 as this can run on GPT4.
 2023-04-12 09:25:43 +01:00
Drikus Roor
f34751a0c3 revert: Revert relative imports in scripts and fix imports in tests 2023-04-12 10:16:00 +02:00
Drikus Roor
d0ae72e63b refactor: Refactor imports to be compatible with unit tests 2023-04-12 10:16:00 +02:00
Richard Beales
c765b345b4 Merge pull request #904 from endolith/typos 
Fix some typos
 2023-04-12 08:50:06 +01:00
Toran Bruce Richards
429317e6b2 Merge pull request #910 from dillweed/Elevenlabs-Voice-ID-ENV 
Elevenlabs voice ID
 2023-04-12 19:26:12 +12:00
Toran Bruce Richards
4c6f18bc59 Merge pull request #878 from Androbin/patch-1 
Fix Spinner
 2023-04-12 19:22:31 +12:00
Peter Edwards
17b037faf7 Merge branch 'Torantulino:master' into more_azure 2023-04-12 09:18:17 +02:00
Toran Bruce Richards
e4bb730826 Merge pull request #759 from BillSchumacher/fix-too-specific-except 
Fix case where index throws value error.
 2023-04-12 18:51:57 +12:00
vadi
7736762b5a Fix #840 - Add defensive coding for local memory to load the JSON file that was gitignored at 54101c7997 
- Added unit test placholder for local cache test
- Removed unused imports from local cache unit test placeholder
 2023-04-12 16:38:53 +10:00
vadi
bc6f34d7dc Fixes #803 
- Brings back debug mode
- Replaces all calls from cfg.debug to cfg.debug_mode that was updated on 5b2d6010dc
- Remove unnecessary config instance at main.py
 2023-04-12 16:32:16 +10:00
Dill
f8438aabc2 Added option for custom elevenlabs voice IDs. 2023-04-11 21:37:03 -07:00
endolith
cf8b06f11f Fix some typos 2023-04-12 00:11:24 -04:00