99f03c33f1
Merge branch 'main' into gemma
2025-08-06 07:49:59 +02:00
39237e6cda
Add OpenAI OSS models to Groq verified and tool calling models
...
Co-authored-by: mailmertunsal <mailmertunsal@gmail.com >
2025-08-05 20:09:54 +00:00
1e2a083415
Merge branch 'main' into local-remote-split
2025-08-05 18:28:06 +01:00
10581b6e77
just improve more
2025-08-05 15:10:23 +01:00
bc9a3a5fbb
just improve
2025-08-05 15:07:50 +01:00
714b5f7d0b
Merge branch 'main' into mert/improve_messages_for_kv_cache
2025-08-05 13:32:59 +01:00
328a4b5be4
Merge branch 'feature/new-dom-extraction-layer' into local-remote-split
2025-08-05 03:12:48 -07:00
2ce156d69e
Merge branch 'main' into mert/custom_model
2025-08-04 20:31:38 +01:00
593f7e7178
Merge branch 'main' into gemma
2025-08-03 20:57:55 +02:00
6ecbf13e3b
bumped up azure api version
2025-08-02 14:24:35 -07:00
0aa3d54233
Merge commit '9b882faa10c54be5a870cc5d8abd6ddb19d0682f' into feature/new-dom-extraction-layer
2025-08-02 11:41:28 -07:00
87e856d319
Merge branch 'main' into fix/gemini-dict-type-field-handling
2025-08-01 20:46:32 +05:30
7d0b2f411c
fix lint errors
2025-07-31 13:22:36 +02:00
6ddeb2324e
extend supported model list
2025-07-31 13:09:57 +02:00
cbc951995b
add gemma support
2025-07-31 13:05:06 +02:00
212be3248b
Support specifying OpenAI service_tier param
2025-07-30 07:50:33 +12:00
cedb0d9cd4
fix: handle unexpected response types in ChatAnthropic
...
- Add type checking before accessing response.usage attribute
- Raise clear ModelProviderError when response is not a Message object
- Prevents AttributeError when API returns string errors instead of proper response
- Fixes issue #2559 where 502 errors caused ''str'' object has no attribute ''usage''
Co-authored-by: Nick Sweeting <pirate@users.noreply.github.com >
2025-07-29 18:09:01 +00:00
5405024889
fix: handle non-string type fields in Gemini schema processing
2025-07-27 10:55:47 +05:30
ce024d25ab
Merge branch 'main' into mert/improve_messages_for_kv_cache
2025-07-25 19:40:02 +02:00
11b3d3113b
Merge branch 'main' into feat/params
2025-07-25 09:50:03 +02:00
75cbb6b0f4
Merge branch 'main' into llm
2025-07-24 19:43:00 +02:00
eb833d34d9
now history is cached
2025-07-23 19:08:50 +02:00
7ebf5eb881
Update chat.py
2025-07-22 18:59:04 +02:00
63cb5613a5
commit
2025-07-22 18:50:17 +02:00
a5bc83f766
Revert "add init to make things library"
2025-07-20 23:57:53 +02:00
b0486a7e23
Merge branch 'main' into mert/fix_lazy_imports
2025-07-20 23:56:34 +02:00
f901a6931f
add init to make things library
2025-07-20 23:55:25 +02:00
d695a56923
fix temperature for reasoning models
2025-07-20 23:53:00 +02:00
76b57a5586
Merge branch 'main' into feat/speed-improvements-wait
2025-07-20 23:23:50 +02:00
d9e6348a67
Include frequency_penalty 0.05
2025-07-20 23:11:23 +02:00
ce5bfe6195
lazy imports and bump some versions
2025-07-20 22:58:34 +02:00
5b13195f56
Increase default temperature to 0.2 to avoid infinite generation
2025-07-20 16:24:41 +02:00
f993349588
first attempt at our own models
2025-07-20 15:55:04 +02:00
6285bfeca0
Enable max tokens for openai and top_p
2025-07-19 19:36:49 +02:00
95009f7d95
Add runtime type check for llm in Agent init
...
Added a type check to ensure the llm argument is an instance of BaseChatModel in Agent's constructor, raising a ValueError otherwise. Also marked BaseChatModel as @runtime_checkable to support isinstance checks.
2025-07-19 13:54:12 +05:30
4525153d24
refactor reasoning_effort_dict to model_params for a more appropriate name
2025-07-17 10:58:09 +03:00
177854d4f2
refactor model_params dict for consistency
2025-07-17 10:56:30 +03:00
460de46c51
add temperature to model params only if it is not None
2025-07-17 10:55:25 +03:00
99f285e25a
Merge branch 'main' into extraction-magnus-revert-with-main-with-extension
2025-07-16 21:51:42 +02:00
6e85f8602d
support tool calling with groq
2025-07-16 11:13:04 +02:00
061e24b976
Merge remote-tracking branch 'origin/main' into extraction-magnus-revert-with-main
2025-07-14 18:35:21 +02:00
7bf17064f6
started migration to pure cdp
2025-07-11 14:19:22 +02:00
b1e4585e71
patch 7 code-style : add deepseek llm chat model
2025-07-11 19:06:39 +08:00
39bd56250f
patch 6 code-style : add deepseek llm chat model
2025-07-11 19:01:32 +08:00
30e1ae65b7
Update __init__.py
2025-07-11 18:49:17 +08:00
0d9e6e3a2f
patch 4 code-style : add deepseek llm chat model
2025-07-11 18:46:57 +08:00
96b12377f1
Update __init__.py
2025-07-11 18:21:35 +08:00
d990ab15df
patch 2 code-style & type-checker : add deepseek llm chat model
2025-07-11 18:03:07 +08:00
e9f539a714
patch code-style & type-checker : add deepseek llm chat model
2025-07-11 17:50:27 +08:00
36e50a739e
add deepseek llm chat model
2025-07-11 17:11:21 +08:00
Goldener Stefan