langchain-ai
langchain
BlogDocsChangelog

fix(openai): Improve vLLM API compatibility and error messages

#33662
Comparing
KaparthyReddy:fix/vllm-null-choices-error
(
663d485
) with
master
(
f174295
)
CodSpeed Performance Gauge
0%
Untouched
6
Skipped
28

Benchmarks

Skipped (28)

test_create_chat_prompt_init_time
libs/partners/prompty/tests/unit_tests/test_standard.py
Skipped
311.9 µs*
test_init_time
libs/partners/groq/tests/unit_tests/test_standard.py::TestGroqStandard
Skipped
1.6 s*
test_exa_retriever_init_time
libs/partners/exa/tests/unit_tests/test_standard.py
Skipped
325.3 µs*
test_chroma_init_time
libs/partners/chroma/tests/unit_tests/test_standard.py
Skipped
59.6 ms*
test_init_time
libs/partners/deepseek/tests/unit_tests/test_chat_models.py::TestChatDeepSeekUnit
Skipped
1.6 s*
test_init_time
libs/partners/ollama/tests/unit_tests/test_chat_models.py::TestChatOllama
Skipped
1.6 s*
test_init_time
libs/partners/fireworks/tests/unit_tests/test_standard.py::TestFireworksStandard
Skipped
6.6 s*
test_nomic_embeddings_init_time
libs/partners/nomic/tests/unit_tests/test_standard.py
Skipped
1.6 ms*
test_stream_time
libs/partners/anthropic/tests/integration_tests/test_standard.py::TestAnthropicStandard
Skipped
35 ms*
test_init_time_with_client
libs/partners/anthropic/tests/unit_tests/test_standard.py
Skipped
2.3 ms*
test_init_time
libs/partners/anthropic/tests/unit_tests/test_standard.py::TestAnthropicStandard
Skipped
793.3 µs*
test_init_time
libs/partners/xai/tests/unit_tests/test_chat_models_standard.py::TestXAIStandard
Skipped
3.3 s*
test_qdrant_vectorstore_init_time
libs/partners/qdrant/tests/unit_tests/test_standard.py
Skipped
225.1 ms*
test_init_time
libs/partners/perplexity/tests/unit_tests/test_chat_models_standard.py::TestPerplexityStandard
Skipped
840.6 ms*
test_init_time
libs/partners/mistralai/tests/unit_tests/test_standard.py::TestMistralStandard
Skipped
9.1 ms*
test_import_time[PydanticOutputParser]
libs/core/tests/benchmarks/test_imports.py
Skipped
515.9 ms*
test_async_callbacks_in_sync
libs/core/tests/benchmarks/test_async_callbacks.py
Skipped
23.6 ms*
test_import_time[CallbackManager]
libs/core/tests/benchmarks/test_imports.py
Skipped
448 ms*
test_import_time[Document]
libs/core/tests/benchmarks/test_imports.py
Skipped
185.7 ms*
test_import_time[InMemoryRateLimiter]
libs/core/tests/benchmarks/test_imports.py
Skipped
172.1 ms*
test_import_time[RunnableLambda]
libs/core/tests/benchmarks/test_imports.py
Skipped
477.3 ms*
test_import_time[tool]
libs/core/tests/benchmarks/test_imports.py
Skipped
497.9 ms*
test_import_time[Runnable]
libs/core/tests/benchmarks/test_imports.py
Skipped
475.9 ms*
test_import_time[ChatPromptTemplate]
libs/core/tests/benchmarks/test_imports.py
Skipped
583.5 ms*
test_import_time[BaseChatModel]
libs/core/tests/benchmarks/test_imports.py
Skipped
511.6 ms*
test_import_time[LangChainTracer]
libs/core/tests/benchmarks/test_imports.py
Skipped
429.5 ms*
test_import_time[HumanMessage]
libs/core/tests/benchmarks/test_imports.py
Skipped
261.9 ms*
test_import_time[InMemoryVectorStore]
libs/core/tests/benchmarks/test_imports.py
Skipped
597 ms*

Passed

test_stream_time
libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py::TestOpenAIResponses
CodSpeed Performance Gauge
0%
856.1 ms*855.8 ms
test_init_time
libs/partners/openai/tests/unit_tests/chat_models/test_azure_standard.py::TestOpenAIStandard
CodSpeed Performance Gauge
0%
1.7 s*1.7 s
test_stream_time
libs/partners/openai/tests/integration_tests/chat_models/test_responses_standard.py::TestOpenAIStandard
CodSpeed Performance Gauge
0%
1.1 s*1.1 s
test_stream_time
libs/partners/openai/tests/integration_tests/chat_models/test_base_standard.py::TestOpenAIStandard
CodSpeed Performance Gauge
0%
1.1 s*1.1 s
test_init_time
libs/partners/openai/tests/unit_tests/chat_models/test_base_standard.py::TestOpenAIStandard
CodSpeed Performance Gauge
0%
12.1 ms*12.1 ms
test_init_time
libs/partners/openai/tests/unit_tests/chat_models/test_responses_standard.py::TestOpenAIResponses
CodSpeed Performance Gauge
0%
12.1 ms*12.1 ms

Commits

Click on a commit to change the comparison range
Base
master
f174295
-0.08%
fix(openai): Improve vLLM API compatibility and error messages - Add robust fallback for response serialization when model_dump() fails - Use model_dump_json() as fallback for non-OpenAI API responses - Improve null choices error message with debugging information - Add tests for vLLM-style responses and improved error messages Fixes #32252
663d485
5 days ago
© 2025 CodSpeed Technology
Home Terms Privacy Docs