phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
litellm-mirror/litellm/llms
History
Krish Dholakia f08a4e3c06
Support 'file' message type for VLLM video url's + Anthropic redacted message thinking support (#10129) 
* feat(hosted_vllm/chat/transformation.py): support calling vllm video url with openai 'file' message type

allows switching between gemini/vllm easily

* [WIP] redacted thinking tests (#9044)

* WIP: redacted thinking tests

* test: add test for redacted thinking in assistant message

---------

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>

* fix(anthropic/chat/transformation.py): support redacted thinking block on anthropic completion

Fixes https://github.com/BerriAI/litellm/issues/9058

* fix(anthropic/chat/handler.py): transform anthropic redacted messages on streaming

Fixes https://github.com/BerriAI/litellm/issues/9058

* fix(bedrock/): support redacted text on streaming + non-streaming

Fixes https://github.com/BerriAI/litellm/issues/9058

* feat(litellm_proxy/chat/transformation.py): support 'reasoning_effort' param for proxy

allows using reasoning effort with thinking models on proxy

* test: update tests

* fix(utils.py): fix linting error

* fix: fix linting errors

* fix: fix linting errors

* fix: fix linting error

* fix: fix linting errors

* fix(anthropic/chat/transformation.py): fix returning citations in chat completion

---------

Co-authored-by: Johann Miller <22018973+johannkm@users.noreply.github.com>
2025-04-19 11:16:37 -07:00
..
ai21/chat (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
aiohttp_openai/chat VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
anthropic Support 'file' message type for VLLM video url's + Anthropic redacted message thinking support (#10129) 2025-04-19 11:16:37 -07:00
azure fix get_azure_client 2025-04-19 08:33:26 -07:00
azure_ai VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
base_llm [Feat] Unified Responses API - Add Azure Responses API support (#10116) 2025-04-17 16:47:59 -07:00
bedrock Support 'file' message type for VLLM video url's + Anthropic redacted message thinking support (#10129) 2025-04-19 11:16:37 -07:00
cerebras (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
clarifai VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
cloudflare/chat VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
codestral/completion build(pyproject.toml): add new dev dependencies - for type checking (#9631) 2025-03-29 11:02:13 -07:00
cohere Updated cohere v2 passthrough (#9997) 2025-04-14 19:51:01 -07:00
custom_httpx Handle fireworks ai tool calling response (#10130) 2025-04-19 09:37:45 -07:00
databricks Support 'file' message type for VLLM video url's + Anthropic redacted message thinking support (#10129) 2025-04-19 11:16:37 -07:00
deepgram VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
deepinfra/chat Squashed commit of the following: (#9709) 2025-04-02 21:24:54 -07:00
deepseek Add Google AI Studio /v1/files upload API support (#9645) 2025-04-02 08:56:58 -07:00
deprecated_providers build(pyproject.toml): add new dev dependencies - for type checking (#9631) 2025-03-29 11:02:13 -07:00
empower/chat LiteLLM Common Base LLM Config (pt.3): Move all OAI compatible providers to base llm config (#7148) 2024-12-10 17:12:42 -08:00
fireworks_ai Handle fireworks ai tool calling response (#10130) 2025-04-19 09:37:45 -07:00
friendliai/chat (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
galadriel/chat (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
gemini Gemini-2.5-flash - support reasoning cost calc + return reasoning content (#10141) 2025-04-19 09:20:52 -07:00
github/chat (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
groq fix(llm_http_handler.py): fix fake streaming (#10061) 2025-04-16 10:15:11 -07:00
hosted_vllm Support 'file' message type for VLLM video url's + Anthropic redacted message thinking support (#10129) 2025-04-19 11:16:37 -07:00
huggingface VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
infinity/rerank add bedrock llama vision support + cohere / infinity rerank - 'return_documents' support (#8684) 2025-02-20 21:23:54 -08:00
jina_ai Add cohere v2/rerank support (#8421) (#8605) 2025-02-22 22:25:29 -08:00
litellm_proxy/chat Support 'file' message type for VLLM video url's + Anthropic redacted message thinking support (#10129) 2025-04-19 11:16:37 -07:00
lm_studio fix: dictionary changed size during iteration error (#8327) (#8341) 2025-02-07 16:20:28 -08:00
mistral fix(mistral_chat_transformation.py): add missing comma (#9606) 2025-03-27 22:16:21 -07:00
nlp_cloud VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
nvidia_nim fix: dictionary changed size during iteration error (#8327) (#8341) 2025-02-07 16:20:28 -08:00
ollama VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
oobabooga VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
openai [Feat] Unified Responses API - Add Azure Responses API support (#10116) 2025-04-17 16:47:59 -07:00
openai_like fix(llm_http_handler.py): fix fake streaming (#10061) 2025-04-16 10:15:11 -07:00
openrouter fix #8425, passthrough kwargs during acompletion, and unwrap extra_body for openrouter (#9747) 2025-04-03 22:19:40 -07:00
perplexity/chat fix missing comma 2025-02-24 01:00:07 +05:30
petals VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
predibase VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
replicate VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
sagemaker VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
sambanova update sambanova docs (#8875) 2025-02-27 20:23:33 -08:00
snowflake VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
together_ai Squashed commit of the following: (#9709) 2025-04-02 21:24:54 -07:00
topaz Add /vllm/* and /mistral/* passthrough endpoints (adds support for Mistral OCR via passthrough) 2025-04-14 22:06:33 -07:00
triton VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
vertex_ai Support 'file' message type for VLLM video url's + Anthropic redacted message thinking support (#10129) 2025-04-19 11:16:37 -07:00
vllm Add /vllm/* and /mistral/* passthrough endpoints (adds support for Mistral OCR via passthrough) 2025-04-14 22:06:33 -07:00
voyage/embedding VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
watsonx VertexAI non-jsonl file storage support (#9781) 2025-04-09 14:01:48 -07:00
xai Add /vllm/* and /mistral/* passthrough endpoints (adds support for Mistral OCR via passthrough) 2025-04-14 22:06:33 -07:00
__init__.py
base.py build(pyproject.toml): add new dev dependencies - for type checking (#9631) 2025-03-29 11:02:13 -07:00
baseten.py test(base_llm_unit_tests.py): add test to ensure drop params is respe… (#8224) 2025-02-03 16:04:44 -08:00
custom_llm.py (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
maritalk.py build(pyproject.toml): add new dev dependencies - for type checking (#9631) 2025-03-29 11:02:13 -07:00
ollama_chat.py Litellm dev 03 08 2025 p3 (#9089) 2025-03-09 18:20:56 -07:00
README.md LiteLLM Minor Fixes and Improvements (09/13/2024) (#5689) 2024-09-14 10:02:55 -07:00
volcengine.py (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00

README.md

File Structure

August 27th, 2024

To make it easy to see how calls are transformed for each model/provider:

we are working on moving all supported litellm providers to a folder structure, where folder name is the supported litellm provider name.

Each folder will contain a *_transformation.py file, which has all the request/response transformation logic, making it easy to see how calls are modified.

E.g. cohere/, bedrock/.