donggyun112:feature/stream-event-name-literal-type - Branch - langchain-ai/langchain

feat(core): add `StreamEventName` `Literal` type for type-safe event handling

#34676

Comparing

donggyun112:feature/stream-event-name-literal-type

(

2179bc9

) with

master

(

2ef2388

)

-3%

Untouched: 13

Skipped: 21

Unknown Walltime execution environment detected

Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data. For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.

Benchmarks

Skipped (21)

Passed

test_import_time[RunnableLambda]

libs/core/tests/benchmarks/test_imports.py

-1%

507.7 ms514.4 ms

test_async_callbacks_in_sync

libs/core/tests/benchmarks/test_async_callbacks.py

-2%

23.8 ms24.2 ms

test_import_time[LangChainTracer]

libs/core/tests/benchmarks/test_imports.py

-2%

450.1 ms461.5 ms

test_import_time[Document]

libs/core/tests/benchmarks/test_imports.py

-3%

189.2 ms194.2 ms

test_import_time[InMemoryRateLimiter]

libs/core/tests/benchmarks/test_imports.py

-3%

174.2 ms178.9 ms

test_import_time[CallbackManager]

libs/core/tests/benchmarks/test_imports.py

-3%

473 ms486.5 ms

test_import_time[Runnable]

libs/core/tests/benchmarks/test_imports.py

-3%

504.6 ms519.6 ms

test_import_time[HumanMessage]

libs/core/tests/benchmarks/test_imports.py

-3%

263.8 ms271.9 ms

test_import_time[ChatPromptTemplate]

libs/core/tests/benchmarks/test_imports.py

-3%

639.3 ms659.3 ms

test_import_time[tool]

libs/core/tests/benchmarks/test_imports.py

-4%

530.2 ms549.5 ms

test_import_time[PydanticOutputParser]

libs/core/tests/benchmarks/test_imports.py

-4%

544 ms564.2 ms

test_import_time[BaseChatModel]

libs/core/tests/benchmarks/test_imports.py

-4%

549.2 ms572.3 ms

test_import_time[InMemoryVectorStore]

libs/core/tests/benchmarks/test_imports.py

-4%

607.5 ms633.2 ms

Commits

Click on a commit to change the comparison range

Base

master

2ef2388

-3.49%

feat(core): add StreamEventName Literal type for type-safe event handling Add StreamEventName Literal type to langchain_core/runnables/schema.py for type-safe event handling in astream_events. Changes: - Add StreamEventName Literal type with 26 event names - Add StreamEventPhase Literal type for event phases - Add get_event_name() helper function with centralized mapping - Update BaseStreamEvent.event field to use StreamEventName - Update event_stream.py to use get_event_name() helper - Add comprehensive tests for new types and helper Supported run_types: llm, chat_model, tool, chain, retriever, prompt, parser Benefits: - IDE autocompletion for event names - Static type checking catches typos at development time - Runtime validation via get_event_name() helper - Fully backward compatible (Literal is str subtype)

9af7620

2 days ago

by donggyun112

+3.04%

Merge branch 'master' into feature/stream-event-name-literal-type

bdc61b7

2 days ago

by donggyun112

-2.44%

Merge branch 'master' into feature/stream-event-name-literal-type

2179bc9

16 hours ago

by donggyun112

Home Terms Privacy Docs