phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Support 'file' message type for VLLM video url's + Anthropic redacted message thinking support (#10129)

Browse source 
* 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>
This commit is contained in:
Krish Dholakia 2025-04-19 11:16:37 -07:00 • committed by GitHub
parent 3c463f6715
commit f08a4e3c06
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 638 additions and 109 deletions
Download patch file Download diff file Expand all files Collapse all files

36
litellm/llms/anthropic/chat/handler.py
View file

@ -29,6 +29,7 @@ from litellm.types.llms.anthropic import (
UsageDelta,
)
from litellm.types.llms.openai import (
ChatCompletionRedactedThinkingBlock,
ChatCompletionThinkingBlock,
ChatCompletionToolCallChunk,
)
@ -501,18 +502,19 @@ class ModelResponseIterator:
) -> Tuple[
str,
Optional[ChatCompletionToolCallChunk],
List[ChatCompletionThinkingBlock],
List[Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]],
Dict[str, Any],
]:
"""
Helper function to handle the content block delta
"""
text = ""
tool_use: Optional[ChatCompletionToolCallChunk] = None
provider_specific_fields = {}
content_block = ContentBlockDelta(**chunk) # type: ignore
thinking_blocks: List[ChatCompletionThinkingBlock] = []
thinking_blocks: List[
Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]
] = []
self.content_blocks.append(content_block)
if "text" in content_block["delta"]:
@ -541,20 +543,25 @@ class ModelResponseIterator:
)
]
provider_specific_fields["thinking_blocks"] = thinking_blocks
return text, tool_use, thinking_blocks, provider_specific_fields
def _handle_reasoning_content(
self, thinking_blocks: List[ChatCompletionThinkingBlock]
self,
thinking_blocks: List[
Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]
],
) -> Optional[str]:
"""
Handle the reasoning content
"""
reasoning_content = None
for block in thinking_blocks:
thinking_content = cast(Optional[str], block.get("thinking"))
if reasoning_content is None:
reasoning_content = ""
if "thinking" in block:
reasoning_content += block["thinking"]
if thinking_content is not None:
reasoning_content += thinking_content
return reasoning_content
def chunk_parser(self, chunk: dict) -> ModelResponseStream:
@ -567,7 +574,13 @@ class ModelResponseIterator:
usage: Optional[Usage] = None
provider_specific_fields: Dict[str, Any] = {}
reasoning_content: Optional[str] = None
thinking_blocks: Optional[List[ChatCompletionThinkingBlock]] = None
thinking_blocks: Optional[
List[
Union[
ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock
]
]
] = None
index = int(chunk.get("index", 0))
if type_chunk == "content_block_delta":
@ -605,6 +618,15 @@ class ModelResponseIterator:
},
"index": self.tool_index,
}
elif (
content_block_start["content_block"]["type"] == "redacted_thinking"
):
thinking_blocks = [
ChatCompletionRedactedThinkingBlock(
type="redacted_thinking",
data=content_block_start["content_block"]["data"],
)
]
elif type_chunk == "content_block_stop":
ContentBlockStop(**chunk) # type: ignore
# check if tool call content block