langchain Architecture Docs
Home / Function/ _clean_block() — langchain Function Reference

_clean_block() — langchain Function Reference

Architecture documentation for the _clean_block() function in chat_models.py from the langchain codebase.

Function python LangChainCore LanguageModelBase called by 1

Entity Profile

Dependency Diagram

graph TD
  30456995_7e1c_8201_cd0a_0ab4e2ee2d00["_clean_block()"]
  cfb937d2_ce7f_5338_2b62_6452043ac78a["chat_models.py"]
  30456995_7e1c_8201_cd0a_0ab4e2ee2d00 -->|defined in| cfb937d2_ce7f_5338_2b62_6452043ac78a
  0040f7d2_abde_821f_7713_ae3da549425c["_convert_message_to_mistral_chat_message()"]
  0040f7d2_abde_821f_7713_ae3da549425c -->|calls| 30456995_7e1c_8201_cd0a_0ab4e2ee2d00
  style 30456995_7e1c_8201_cd0a_0ab4e2ee2d00 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/mistralai/langchain_mistralai/chat_models.py lines 357–369

def _clean_block(block: dict) -> dict:
    # Remove "index" key added for message aggregation in langchain-core
    new_block = {k: v for k, v in block.items() if k != "index"}
    if block.get("type") == "thinking" and isinstance(block.get("thinking"), list):
        new_block["thinking"] = [
            (
                {k: v for k, v in sb.items() if k != "index"}
                if isinstance(sb, dict) and "index" in sb
                else sb
            )
            for sb in block["thinking"]
        ]
    return new_block

Domain

Subdomains

Defined In

Called By

Source

Frequently Asked Questions

What does _clean_block() do?
_clean_block() is a function in the langchain codebase, defined in libs/partners/mistralai/langchain_mistralai/chat_models.py.
Where is _clean_block() defined?
_clean_block() is defined in libs/partners/mistralai/langchain_mistralai/chat_models.py at line 357.
What calls _clean_block()?
_clean_block() is called by 1 function(s): _convert_message_to_mistral_chat_message.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free