Commit Graph

23 Commits

Author SHA1 Message Date
mamoodi
e6a5e39047 Update docs associated with new UI (#4469) 2024-10-18 10:19:56 -04:00
OpenHands
ff8a9a1a56 Fix issue #4225: Add evaluation data to the LLMs docs (#4312)
Co-authored-by: Graham Neubig <neubig@gmail.com>
2024-10-13 11:12:12 -07:00
Robert Brennan
42c118f4b4 Add Getting Started docs (#4224) 2024-10-05 14:21:02 +00:00
mamoodi
04643d6f3c Make Claude Sonnet 3.5 the recommended model and update docs accordingly (#4151) 2024-10-01 20:32:39 +00:00
Engel Nyst
0a03c802f5 Refactor llm.py (#4057) 2024-09-26 17:44:18 +00:00
mamoodi
e0608af0b3 Add OpenRouter provider docs (#3986) 2024-09-21 20:57:25 -04:00
mamoodi
ef189d52a5 Remove ollama reference from documentation for now (#3959) 2024-09-20 14:48:48 -04:00
mamoodi
9d4eb7d19d Minor tweaks to getting started guide (#3901) 2024-09-16 13:53:46 -04:00
mamoodi
a97ef34139 documentation changes associated with UI changes and more consistency (#3866) 2024-09-14 17:22:15 -04:00
tobitege
03b5b03bb2 (enh) CodeActAgent: improve logging; sensible retry defaults in config (#3729)
* CodeActAgent: improve logging; sensible retry defaults for completion errors

* CodeActAgent: reduce completion error message sent to UI

* tweak values; docs+config template changes

* fix format_messages; log exception in codeactagent again
2024-09-05 18:14:15 +00:00
niliy01
82a154f7e7 (feat) making prompt caching optional instead of enabled default (#3689)
* (feat) making prompt caching optional instead of enabled default

At present, only the Claude models support prompt caching as a experimental feature, therefore, this feature should be implemented as an optional setting rather than being enabled by default.

Signed-off-by: Yi Lin <teroincn@gmail.com>

* handle the conflict

* fix unittest mock return value

* fix lint error in whitespace

---------

Signed-off-by: Yi Lin <teroincn@gmail.com>
2024-09-05 18:52:26 +02:00
mamoodi
60c5fd41ec Update docs on LLM providers for consistency (#3738)
* Update docs on LLM providers for consistency

* Update headless command

* minor tweaks based on feedback

---------

Co-authored-by: Robert Brennan <contact@rbren.io>
Co-authored-by: Robert Brennan <accounts@rbren.io>
2024-09-05 15:10:28 +00:00
Robert Brennan
2a99aa6679 Cosmetic README updates (#3728)
* update badges

* fix badges

* better badges

* move credits

* more badge work

* add gh logo

* update some copy

* update logo

* fix height

* update text

* emdash

* remove cruft

* move title

* update links

* add hr

* white logo

* move some stuff to getting-started

* revert logo

* more copy changes

* minor tweaks

* words

* fix getting started

* update to 0.9.2

* update screenshot

* minor fixes
2024-09-04 19:38:28 +00:00
tobitege
bc31fb15fe (fix) CodeActAgent: fix issues with vision support in prompts (#3665)
* CodeActAgent: fix message prep if prompt caching is not supported

* fix python version in regen tests workflow

* fix in conftest "mock_completion" method

* add disable_vision to LLMConfig; revert change in message parsing in llm.py

* format messages in several files for completion

* refactored message(s) formatting (llm.py); added vision_is_active()

* fix a unit test

* regenerate: added LOG_TO_FILE and FORCE_REGENERATE env flags

* try to fix path to logs folder in workflow

* llm: prevent index error

* try FORCE_USE_LLM in regenerate

* tweaks everywhere...

* fix 2 random unit test errors :(

* added FORCE_REGENERATE_TESTS=true to regenerate CLI

* fix test_lint_file_fail_typescript again

* double-quotes for env vars in workflow; llm logger set to debug

* fix typo in regenerate

* regenerate iterations now 20; applied iteration counter fix by Li

* regenerate: pass FORCE_REGENERATE flag into env

* fixes for int tests. several mock files updated.

* browsing_agent: fix response_parser.py adding ) to empty response

* test_browse_internet: fix skipif and revert obsolete mock files

* regenerate: fi bracketing for http server start/kill conditions

* disable test_browse_internet for CodeAct*Agents; mock files updated after merge

* missed to include more mock files earlier

* reverts after review feedback from Li

* forgot one

* browsing agent test, partial fixes and updated mock files

* test_browse_internet works in my WSL now!

* adapt unit test test_prompt_caching.py

* add DEBUG to regenerate workflow command

* convert regenerate workflow params to inputs

* more integration test mock files updated

* more files

* test_prompt_caching: restored test_prompt_caching_headers purpose

* file_ops: fix potential exception, like "cross device copy"; fixed mock files accordingly

* reverts/changes wrt feedback from xingyao

* updated docs and config template

* code cleanup wrt review feedback
2024-09-04 17:58:30 +02:00
mamoodi
510a82a039 Verified list of LLMs working with OpenHands and some LLM doc changes (#3714)
* Verified list of LLMs working with OpenHands and some LLM doc changes

* Update list of verified

* Add warning for ollama guide
2024-09-03 13:14:38 -04:00
mamoodi
212a78c703 docs: More consistent documentation (#3608) 2024-08-27 16:04:13 +02:00
sp.wack
6180483fac docs: Update to include guide for OpenAI LLMs (#3552)
* Update docs to include OpenAI LLMs

* Remove broken link

* Update docs/modules/usage/llms/openai-llms.md
2024-08-23 16:00:04 +03:00
Robert Brennan
01ae22ef57 Rename OpenDevin to OpenHands (#3472)
* Replace OpenDevin with OpenHands

* Update CONTRIBUTING.md

* Update README.md

* Update README.md

* update poetry lock; move opendevin folder to openhands

* fix env var

* revert image references in docs

* revert permissions

* revert permissions

---------

Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>
2024-08-20 00:44:54 +08:00
mamoodi
14a4e45cbb Standardize names and better organization (#3453)
* Standardize names and better organization

* Update links
2024-08-19 09:30:47 +08:00
tobitege
d50a8447ad fix: add llm drop_params parameter to LLMConfig (#2471)
* feat: add drop_params to LLMConfig

* Update opendevin/llm/llm.py

Fix use of unknown method.

Co-authored-by: மனோஜ்குமார் பழனிச்சாமி <smartmanoj42857@gmail.com>

---------

Co-authored-by: மனோஜ்குமார் பழனிச்சாமி <smartmanoj42857@gmail.com>
2024-07-24 16:25:36 +02:00
mamoodi
00542432bd docs: Update documentation with some consistency (#2706)
* Update documentation with some consistency

* Make windows troubleshooting a little more clear

* Apply suggestions from code review

Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>

---------

Co-authored-by: Mahmoud Work <mahmoudwork@mahmouds-mini.home>
Co-authored-by: Boxuan Li <liboxuan@connect.hku.hk>
2024-06-30 23:27:58 +00:00
mamoodi
1d8402a14a doc: Small fixes to documentation (#1783) 2024-05-14 13:36:53 -04:00
Alex Bäuerle
cd58194d2a docs(docs): start implementing docs website (#1372)
* docs(docs): start implementing docs website

* update video url

* add autogenerated codebase docs for backend

* precommit

* update links

* fix config and video

* gh actions

* rename

* workdirs

* path

* path

* fix doc1

* redo markdown

* docs

* change main folder name

* simplify readme

* add back architecture

* Fix lint errors

* lint

* update poetry lock

---------

Co-authored-by: Jim Su <jimsu@protonmail.com>
2024-04-29 10:00:51 -07:00