langchain Architecture Docs
Home / File/ _compat.py — langchain Source File

_compat.py — langchain Source File

Architecture documentation for _compat.py, a python file in the langchain codebase. 3 imports, 0 dependents.

File python LangChainCore MessageInterface 3 imports 2 functions

Entity Profile

Dependency Diagram

graph LR
  229dd2f8_cd21_122c_8dc9_e4e6685d089f["_compat.py"]
  9d14ea65_8b2e_6721_a947_acc89905651f["json"]
  229dd2f8_cd21_122c_8dc9_e4e6685d089f --> 9d14ea65_8b2e_6721_a947_acc89905651f
  feec1ec4_6917_867b_d228_b134d0ff8099["typing"]
  229dd2f8_cd21_122c_8dc9_e4e6685d089f --> feec1ec4_6917_867b_d228_b134d0ff8099
  9444498b_8066_55c7_b3a2_1d90c4162a32["langchain_core.messages"]
  229dd2f8_cd21_122c_8dc9_e4e6685d089f --> 9444498b_8066_55c7_b3a2_1d90c4162a32
  style 229dd2f8_cd21_122c_8dc9_e4e6685d089f fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

from __future__ import annotations

import json
from typing import Any, cast

from langchain_core.messages import content as types


def _convert_annotation_from_v1(annotation: types.Annotation) -> dict[str, Any]:
    """Convert LangChain annotation format to Anthropic's native citation format."""
    if annotation["type"] == "non_standard_annotation":
        return annotation["value"]

    if annotation["type"] == "citation":
        if "url" in annotation:
            # web_search_result_location
            out: dict[str, Any] = {}
            if cited_text := annotation.get("cited_text"):
                out["cited_text"] = cited_text
            if "encrypted_index" in annotation.get("extras", {}):
                out["encrypted_index"] = annotation.get("extras", {})["encrypted_index"]
            if "title" in annotation:
                out["title"] = annotation["title"]
            out["type"] = "web_search_result_location"
            out["url"] = annotation.get("url")

            for key, value in annotation.get("extras", {}).items():
                if key not in out:
                    out[key] = value

            return out

        if "start_char_index" in annotation.get("extras", {}):
            # char_location
            out = {"type": "char_location"}
            for field in ["cited_text"]:
                if value := annotation.get(field):
                    out[field] = value
            if title := annotation.get("title"):
                out["document_title"] = title

            for key, value in annotation.get("extras", {}).items():
                out[key] = value
            out = {k: out[k] for k in sorted(out)}

            return out

        if "search_result_index" in annotation.get("extras", {}):
            # search_result_location
            out = {"type": "search_result_location"}
            for field in ["cited_text", "title"]:
                if value := annotation.get(field):
                    out[field] = value

            for key, value in annotation.get("extras", {}).items():
                out[key] = value

            return out

        if "start_block_index" in annotation.get("extras", {}):
// ... (140 more lines)

Domain

Subdomains

Functions

Dependencies

  • json
  • langchain_core.messages
  • typing

Source

Frequently Asked Questions

What does _compat.py do?
_compat.py is a source file in the langchain codebase, written in python. It belongs to the LangChainCore domain, MessageInterface subdomain.
What functions are defined in _compat.py?
_compat.py defines 2 function(s): _convert_annotation_from_v1, _convert_from_v1_to_anthropic.
What does _compat.py depend on?
_compat.py imports 3 module(s): json, langchain_core.messages, typing.
Where is _compat.py in the architecture?
_compat.py is located at libs/partners/anthropic/langchain_anthropic/_compat.py (domain: LangChainCore, subdomain: MessageInterface, directory: libs/partners/anthropic/langchain_anthropic).

Analyze Your Own Codebase

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

Try Supermodel Free