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

Add property ordering for vertex ai schema (#9828) + Fix combining multiple tool calls (#10040)

Browse source 
* fix #9783: Retain schema field ordering for google gemini and vertex (#9828)

* test: update test

* refactor(groq.py): initial commit migrating groq to base_llm_http_handler

* fix(streaming_chunk_builder_utils.py): fix how tool content is combined

Fixes https://github.com/BerriAI/litellm/issues/10034

* fix(vertex_ai/common_utils.py): prevent infinite loop in helper function

* fix(groq/chat/transformation.py): handle groq streaming errors correctly

* fix(groq/chat/transformation.py): handle max_retries

---------

Co-authored-by: Adrian Lyjak <adrian@chatmeter.com>
This commit is contained in:
Krish Dholakia 2025-04-15 22:29:25 -07:00 • committed by GitHub
parent 1b9b745cae
commit fdfa1108a6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 493 additions and 201 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/llms/custom_httpx/llm_http_handler.py
View file

@ -230,6 +230,7 @@ class BaseLLMHTTPHandler:
client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
):
json_mode: bool = optional_params.pop("json_mode", False)
extra_body: Optional[dict] = optional_params.pop("extra_body", None)
provider_config = ProviderConfigManager.get_provider_chat_config(
model=model, provider=litellm.LlmProviders(custom_llm_provider)
@ -267,6 +268,9 @@ class BaseLLMHTTPHandler:
headers=headers,
)
if extra_body is not None:
data = {**data, **extra_body}
headers = provider_config.sign_request(
headers=headers,
optional_params=optional_params,