langchain/libs/cli
ccurme 22d1a7d7b6
standard-tests[patch]: require model_name in response_metadata if returns_usage_metadata (#30497)
We are implementing a token-counting callback handler in
`langchain-core` that is intended to work with all chat models
supporting usage metadata. The callback will aggregate usage metadata by
model. This requires responses to include the model name in its
metadata.

To support this, if a model `returns_usage_metadata`, we check that it
includes a string model name in its `response_metadata` in the
`"model_name"` key.

More context: https://github.com/langchain-ai/langchain/pull/30487
2025-03-26 12:20:53 -04:00
..
langchain_cli standard-tests[patch]: require model_name in response_metadata if returns_usage_metadata (#30497) 2025-03-26 12:20:53 -04:00
scripts cli: standard tests in cli, test that they run, skip vectorstore tests (#28521) 2024-12-05 00:38:32 -08:00
tests cli: standard tests in cli, test that they run, skip vectorstore tests (#28521) 2024-12-05 00:38:32 -08:00
.gitignore cli: standard tests in cli, test that they run, skip vectorstore tests (#28521) 2024-12-05 00:38:32 -08:00
CONTRIBUTING.md Adds version CLI command (#12619) 2023-10-31 14:50:04 -07:00
DOCS.md Adds version CLI command (#12619) 2023-10-31 14:50:04 -07:00
LICENSE Library Licenses (#13300) 2023-11-28 17:34:27 -08:00
Makefile core[patch]: update structured output tracing (#30123) 2025-03-07 13:05:25 -05:00
poetry.toml Use an in-project virtualenv in the CLI package. (#12678) 2023-10-31 14:51:24 -07:00
pyproject.toml cli: use pytest-watcher (#30465) 2025-03-24 18:06:31 +00:00
README.md templates,docs: leave templates in v0.2 (#27952) 2024-11-07 22:23:48 +00:00
uv.lock cli: use pytest-watcher (#30465) 2025-03-24 18:06:31 +00:00

langchain-cli

This package implements the official CLI for LangChain. Right now, it is most useful for getting started with LangChain Templates!

CLI Docs