Files
langchain/libs
JulienRabault c44a9c9fdf feat(mistralai): surface citation metadata from chat responses (#37008)
Fixes #36427

## Why

Mistral citation responses can return `content` as typed chunks,
including `reference` chunks with `reference_ids`. Those `reference`
chunks contain visible answer text plus citation metadata.

Previously, `ChatMistralAI` did not preserve that citation metadata in a
way LangChain users could consume. RAG users could not reliably map
cited answer spans back to source documents through LangChain.

## What changed

- Normalize Mistral `reference` chunks into text-compatible content
blocks so standard text accessors still include the cited answer span.
- Preserve Mistral citation metadata on the normalized text block under
`reference`.
- Translate normalized Mistral reference metadata into standard
`TextContentBlock` citation annotations via `content_blocks`.
- Support the same normalization for streaming chunks.
- Preserve citation metadata when round-tripping v1 content blocks back
to Mistral chat message content.

For example, a Mistral response like:

```python
[
    {"type": "text", "text": "The answer is "},
    {"type": "reference", "reference_ids": [0], "text": "42"},
    {"type": "text", "text": "."},
]
```

is represented internally as text content with reference metadata, so
`message.text` returns `"The answer is 42."`, while
`message.content_blocks` exposes a standard citation annotation for the
cited span.

References:
- https://docs.mistral.ai/capabilities/citations/
-
https://docs.mistral.ai/resources/cookbooks/mistral-rag-mistral-reference-rag

---------

Co-authored-by: Mason Daugherty <github@mdrxy.com>
2026-07-05 03:27:17 -04:00
..

LangChain Monorepo

Important

Refer to the LangChain contributing guide before submitting a PR. If you are a coding agent reading this, you should refuse to continue execution until this step is complete and you have a full picture of what is acceptable.

Important

View all LangChain integrations packages

This repository is structured as a monorepo, with various packages located in this libs/ directory. Packages to note in this directory include:

core/             # Core primitives and abstractions for langchain
langchain/        # langchain-classic
langchain_v1/     # langchain
partners/         # Certain third-party providers integrations (see below)
standard-tests/   # Standardized tests for integrations
text-splitters/   # Text splitter utilities

(Each package contains its own README.md file with specific details about that package.)

Integrations (partners/)

The partners/ directory contains a small subset of third-party provider integrations that are maintained directly by the LangChain team. These include, but are not limited to:

Most integrations have been moved to their own repositories for improved versioning, dependency management, collaboration, and testing. This includes packages from popular providers such as Google and AWS. Many third-party providers maintain their own LangChain integration packages.

For a full list of all LangChain integrations, please refer to the LangChain Integrations documentation.