langchain-core 1.0.0a1__py3-none-any.whl → 1.0.0a3__py3-none-any.whl

langchain_core/messages/base.py

@@ -150,7 +150,8 @@ class BaseMessage(Serializable):
     def get_lc_namespace(cls) -> list[str]:
         """Get the namespace of the langchain object.
 
-        Default is ["langchain", "schema", "messages"].
+        Returns:
+            ``["langchain", "schema", "messages"]``
         """
         return ["langchain", "schema", "messages"]
 
@@ -179,14 +180,14 @@ class BaseMessage(Serializable):
         .. versionadded:: 1.0.0
 
         """  # noqa: E501
-        from langchain_core.messages import content as types
-        from langchain_core.messages.block_translators.anthropic import (
+        from langchain_core.messages import content as types  # noqa: PLC0415
+        from langchain_core.messages.block_translators.anthropic import (  # noqa: PLC0415
             _convert_to_v1_from_anthropic_input,
         )
-        from langchain_core.messages.block_translators.langchain_v0 import (
+        from langchain_core.messages.block_translators.langchain_v0 import (  # noqa: PLC0415
             _convert_v0_multimodal_input_to_v1,
         )
-        from langchain_core.messages.block_translators.openai import (
+        from langchain_core.messages.block_translators.openai import (  # noqa: PLC0415
             _convert_to_v1_from_chat_completions_input,
         )
 
@@ -246,8 +247,16 @@ class BaseMessage(Serializable):
         return TextAccessor(text_value)
 
     def __add__(self, other: Any) -> ChatPromptTemplate:
-        """Concatenate this message with another message."""
-        from langchain_core.prompts.chat import ChatPromptTemplate
+        """Concatenate this message with another message.
+
+        Args:
+            other: Another message to concatenate with this one.
+
+        Returns:
+            A ChatPromptTemplate containing both messages.
+        """
+        # Import locally to prevent circular imports.
+        from langchain_core.prompts.chat import ChatPromptTemplate  # noqa: PLC0415
 
         prompt = ChatPromptTemplate(messages=[self])
         return prompt + other

langchain_core/messages/block_translators/__init__.py

@@ -53,26 +53,28 @@ def _register_translators() -> None:
     For translators implemented outside langchain-core, they can be registered by
     calling ``register_translator`` from within the integration package.
     """
-    from langchain_core.messages.block_translators.anthropic import (
+    from langchain_core.messages.block_translators.anthropic import (  # noqa: PLC0415
         _register_anthropic_translator,
     )
-    from langchain_core.messages.block_translators.bedrock import (
+    from langchain_core.messages.block_translators.bedrock import (  # noqa: PLC0415
         _register_bedrock_translator,
     )
-    from langchain_core.messages.block_translators.bedrock_converse import (
+    from langchain_core.messages.block_translators.bedrock_converse import (  # noqa: PLC0415
         _register_bedrock_converse_translator,
     )
-    from langchain_core.messages.block_translators.google_genai import (
+    from langchain_core.messages.block_translators.google_genai import (  # noqa: PLC0415
         _register_google_genai_translator,
     )
-    from langchain_core.messages.block_translators.google_vertexai import (
+    from langchain_core.messages.block_translators.google_vertexai import (  # noqa: PLC0415
         _register_google_vertexai_translator,
     )
-    from langchain_core.messages.block_translators.groq import _register_groq_translator
-    from langchain_core.messages.block_translators.ollama import (
+    from langchain_core.messages.block_translators.groq import (  # noqa: PLC0415
+        _register_groq_translator,
+    )
+    from langchain_core.messages.block_translators.ollama import (  # noqa: PLC0415
         _register_ollama_translator,
     )
-    from langchain_core.messages.block_translators.openai import (
+    from langchain_core.messages.block_translators.openai import (  # noqa: PLC0415
         _register_openai_translator,
     )
 

langchain_core/messages/block_translators/anthropic.py

@@ -443,7 +443,9 @@ def _register_anthropic_translator() -> None:
 
     Run automatically when the module is imported.
     """
-    from langchain_core.messages.block_translators import register_translator
+    from langchain_core.messages.block_translators import (  # noqa: PLC0415
+        register_translator,
+    )
 
     register_translator("anthropic", translate_content, translate_content_chunk)
 

langchain_core/messages/block_translators/bedrock.py

@@ -37,7 +37,9 @@ def _register_bedrock_translator() -> None:
 
     Run automatically when the module is imported.
     """
-    from langchain_core.messages.block_translators import register_translator
+    from langchain_core.messages.block_translators import (  # noqa: PLC0415
+        register_translator,
+    )
 
     register_translator("bedrock", translate_content, translate_content_chunk)
 

langchain_core/messages/block_translators/bedrock_converse.py

@@ -39,7 +39,9 @@ def _register_bedrock_converse_translator() -> None:
 
     Run automatically when the module is imported.
     """
-    from langchain_core.messages.block_translators import register_translator
+    from langchain_core.messages.block_translators import (  # noqa: PLC0415
+        register_translator,
+    )
 
     register_translator("bedrock_converse", translate_content, translate_content_chunk)
 

langchain_core/messages/block_translators/google_genai.py

@@ -37,7 +37,9 @@ def _register_google_genai_translator() -> None:
 
     Run automatically when the module is imported.
     """
-    from langchain_core.messages.block_translators import register_translator
+    from langchain_core.messages.block_translators import (  # noqa: PLC0415
+        register_translator,
+    )
 
     register_translator("google_genai", translate_content, translate_content_chunk)
 

langchain_core/messages/block_translators/google_vertexai.py

@@ -39,7 +39,9 @@ def _register_google_vertexai_translator() -> None:
 
     Run automatically when the module is imported.
     """
-    from langchain_core.messages.block_translators import register_translator
+    from langchain_core.messages.block_translators import (  # noqa: PLC0415
+        register_translator,
+    )
 
     register_translator("google_vertexai", translate_content, translate_content_chunk)
 

langchain_core/messages/block_translators/groq.py

@@ -37,7 +37,9 @@ def _register_groq_translator() -> None:
 
     Run automatically when the module is imported.
     """
-    from langchain_core.messages.block_translators import register_translator
+    from langchain_core.messages.block_translators import (  # noqa: PLC0415
+        register_translator,
+    )
 
     register_translator("groq", translate_content, translate_content_chunk)
 

langchain_core/messages/block_translators/langchain_v0.py

@@ -2,7 +2,6 @@
 
 from typing import Any, Union, cast
 
-from langchain_core.language_models._utils import _parse_data_uri
 from langchain_core.messages import content as types
 
 
@@ -11,14 +10,15 @@ def _convert_v0_multimodal_input_to_v1(
 ) -> list[types.ContentBlock]:
     """Convert v0 multimodal blocks to v1 format.
 
-    Processes non_standard blocks that might be v0 format and converts them
-    to proper v1 ContentBlocks.
+    Processes ``'non_standard'`` blocks that might be v0 format and converts them
+    to proper v1 ``ContentBlock``.
 
     Args:
         blocks: List of content blocks to process.
 
     Returns:
         Updated list with v0 blocks converted to v1 format.
+
     """
     converted_blocks = []
     unpacked_blocks: list[dict[str, Any]] = [
@@ -162,136 +162,3 @@ def _convert_legacy_v0_content_block_to_v1(
 
     # If we can't convert, return the block unchanged
     return block
-
-
-def _convert_openai_format_to_data_block(
-    block: dict,
-) -> Union[types.ContentBlock, dict[Any, Any]]:
-    """Convert OpenAI image/audio/file content block to respective v1 multimodal block.
-
-    We expect that the incoming block is verified to be in OpenAI Chat Completions
-    format.
-
-    If parsing fails, passes block through unchanged.
-
-    Mappings (Chat Completions to LangChain v1):
-    - Image -> `ImageContentBlock`
-    - Audio -> `AudioContentBlock`
-    - File -> `FileContentBlock`
-
-    """
-
-    # Extract extra keys to put them in `extras`
-    def _extract_extras(block_dict: dict, known_keys: set[str]) -> dict[str, Any]:
-        """Extract unknown keys from block to preserve as extras."""
-        return {k: v for k, v in block_dict.items() if k not in known_keys}
-
-    # base64-style image block
-    if (block["type"] == "image_url") and (
-        parsed := _parse_data_uri(block["image_url"]["url"])
-    ):
-        known_keys = {"type", "image_url"}
-        extras = _extract_extras(block, known_keys)
-
-        # Also extract extras from nested image_url dict
-        image_url_known_keys = {"url"}
-        image_url_extras = _extract_extras(block["image_url"], image_url_known_keys)
-
-        # Merge extras
-        all_extras = {**extras}
-        for key, value in image_url_extras.items():
-            if key == "detail":  # Don't rename
-                all_extras["detail"] = value
-            else:
-                all_extras[f"image_url_{key}"] = value
-
-        return types.create_image_block(
-            # Even though this is labeled as `url`, it can be base64-encoded
-            base64=parsed["data"],
-            mime_type=parsed["mime_type"],
-            **all_extras,
-        )
-
-    # url-style image block
-    if (block["type"] == "image_url") and isinstance(
-        block["image_url"].get("url"), str
-    ):
-        known_keys = {"type", "image_url"}
-        extras = _extract_extras(block, known_keys)
-
-        image_url_known_keys = {"url"}
-        image_url_extras = _extract_extras(block["image_url"], image_url_known_keys)
-
-        all_extras = {**extras}
-        for key, value in image_url_extras.items():
-            if key == "detail":  # Don't rename
-                all_extras["detail"] = value
-            else:
-                all_extras[f"image_url_{key}"] = value
-
-        return types.create_image_block(
-            url=block["image_url"]["url"],
-            **all_extras,
-        )
-
-    # base64-style audio block
-    # audio is only represented via raw data, no url or ID option
-    if block["type"] == "input_audio":
-        known_keys = {"type", "input_audio"}
-        extras = _extract_extras(block, known_keys)
-
-        # Also extract extras from nested audio dict
-        audio_known_keys = {"data", "format"}
-        audio_extras = _extract_extras(block["input_audio"], audio_known_keys)
-
-        all_extras = {**extras}
-        for key, value in audio_extras.items():
-            all_extras[f"audio_{key}"] = value
-
-        return types.create_audio_block(
-            base64=block["input_audio"]["data"],
-            mime_type=f"audio/{block['input_audio']['format']}",
-            **all_extras,
-        )
-
-    # id-style file block
-    if block.get("type") == "file" and "file_id" in block.get("file", {}):
-        known_keys = {"type", "file"}
-        extras = _extract_extras(block, known_keys)
-
-        file_known_keys = {"file_id"}
-        file_extras = _extract_extras(block["file"], file_known_keys)
-
-        all_extras = {**extras}
-        for key, value in file_extras.items():
-            all_extras[f"file_{key}"] = value
-
-        return types.create_file_block(
-            file_id=block["file"]["file_id"],
-            **all_extras,
-        )
-
-    # base64-style file block
-    if (block["type"] == "file") and (
-        parsed := _parse_data_uri(block["file"]["file_data"])
-    ):
-        known_keys = {"type", "file"}
-        extras = _extract_extras(block, known_keys)
-
-        file_known_keys = {"file_data", "filename"}
-        file_extras = _extract_extras(block["file"], file_known_keys)
-
-        all_extras = {**extras}
-        for key, value in file_extras.items():
-            all_extras[f"file_{key}"] = value
-
-        filename = block["file"].get("filename")
-        return types.create_file_block(
-            base64=parsed["data"],
-            mime_type="application/pdf",
-            filename=filename,
-            **all_extras,
-        )
-
-    # Escape hatch
-    return block

langchain_core/messages/block_translators/ollama.py

@@ -37,7 +37,9 @@ def _register_ollama_translator() -> None:
 
     Run automatically when the module is imported.
     """
-    from langchain_core.messages.block_translators import register_translator
+    from langchain_core.messages.block_translators import (  # noqa: PLC0415
+        register_translator,
+    )
 
     register_translator("ollama", translate_content, translate_content_chunk)
 

langchain_core/messages/block_translators/openai.py

@@ -3,21 +3,128 @@
 from __future__ import annotations
 
 import json
+import warnings
 from collections.abc import Iterable
-from typing import TYPE_CHECKING, Any, Optional, Union, cast
+from typing import TYPE_CHECKING, Any, Literal, Optional, Union, cast
 
 from langchain_core.language_models._utils import (
-    _is_openai_data_block,
+    _parse_data_uri,
+    is_openai_data_block,
 )
 from langchain_core.messages import content as types
-from langchain_core.messages.block_translators.langchain_v0 import (
-    _convert_openai_format_to_data_block,
-)
 
 if TYPE_CHECKING:
     from langchain_core.messages import AIMessage, AIMessageChunk
 
 
+def convert_to_openai_image_block(block: dict[str, Any]) -> dict:
+    """Convert ``ImageContentBlock`` to format expected by OpenAI Chat Completions."""
+    if "url" in block:
+        return {
+            "type": "image_url",
+            "image_url": {
+                "url": block["url"],
+            },
+        }
+    if "base64" in block or block.get("source_type") == "base64":
+        if "mime_type" not in block:
+            error_message = "mime_type key is required for base64 data."
+            raise ValueError(error_message)
+        mime_type = block["mime_type"]
+        base64_data = block["data"] if "data" in block else block["base64"]
+        return {
+            "type": "image_url",
+            "image_url": {
+                "url": f"data:{mime_type};base64,{base64_data}",
+            },
+        }
+    error_message = "Unsupported source type. Only 'url' and 'base64' are supported."
+    raise ValueError(error_message)
+
+
+def convert_to_openai_data_block(
+    block: dict, api: Literal["chat/completions", "responses"] = "chat/completions"
+) -> dict:
+    """Format standard data content block to format expected by OpenAI.
+
+    "Standard data content block" can include old-style LangChain v0 blocks
+    (URLContentBlock, Base64ContentBlock, IDContentBlock) or new ones.
+    """
+    if block["type"] == "image":
+        chat_completions_block = convert_to_openai_image_block(block)
+        if api == "responses":
+            formatted_block = {
+                "type": "input_image",
+                "image_url": chat_completions_block["image_url"]["url"],
+            }
+            if chat_completions_block["image_url"].get("detail"):
+                formatted_block["detail"] = chat_completions_block["image_url"][
+                    "detail"
+                ]
+        else:
+            formatted_block = chat_completions_block
+
+    elif block["type"] == "file":
+        if block.get("source_type") == "base64" or "base64" in block:
+            # Handle v0 format (Base64CB): {"source_type": "base64", "data": "...", ...}
+            # Handle v1 format (IDCB): {"base64": "...", ...}
+            base64_data = block["data"] if "source_type" in block else block["base64"]
+            file = {"file_data": f"data:{block['mime_type']};base64,{base64_data}"}
+            if filename := block.get("filename"):
+                file["filename"] = filename
+            elif (extras := block.get("extras")) and ("filename" in extras):
+                file["filename"] = extras["filename"]
+            elif (extras := block.get("metadata")) and ("filename" in extras):
+                # Backward compat
+                file["filename"] = extras["filename"]
+            else:
+                # Can't infer filename
+                warnings.warn(
+                    "OpenAI may require a filename for file uploads. Specify a filename"
+                    " in the content block, e.g.: {'type': 'file', 'mime_type': "
+                    "'...', 'base64': '...', 'filename': 'my-file.pdf'}",
+                    stacklevel=1,
+                )
+            formatted_block = {"type": "file", "file": file}
+            if api == "responses":
+                formatted_block = {"type": "input_file", **formatted_block["file"]}
+        elif block.get("source_type") == "id" or "file_id" in block:
+            # Handle v0 format (IDContentBlock): {"source_type": "id", "id": "...", ...}
+            # Handle v1 format (IDCB): {"file_id": "...", ...}
+            file_id = block["id"] if "source_type" in block else block["file_id"]
+            formatted_block = {"type": "file", "file": {"file_id": file_id}}
+            if api == "responses":
+                formatted_block = {"type": "input_file", **formatted_block["file"]}
+        elif "url" in block:  # Intentionally do not check for source_type="url"
+            if api == "chat/completions":
+                error_msg = "OpenAI Chat Completions does not support file URLs."
+                raise ValueError(error_msg)
+            # Only supported by Responses API; return in that format
+            formatted_block = {"type": "input_file", "file_url": block["url"]}
+        else:
+            error_msg = "Keys base64, url, or file_id required for file blocks."
+            raise ValueError(error_msg)
+
+    elif block["type"] == "audio":
+        if "base64" in block or block.get("source_type") == "base64":
+            # Handle v0 format: {"source_type": "base64", "data": "...", ...}
+            # Handle v1 format: {"base64": "...", ...}
+            base64_data = block["data"] if "source_type" in block else block["base64"]
+            audio_format = block["mime_type"].split("/")[-1]
+            formatted_block = {
+                "type": "input_audio",
+                "input_audio": {"data": base64_data, "format": audio_format},
+            }
+        else:
+            error_msg = "Key base64 is required for audio blocks."
+            raise ValueError(error_msg)
+    else:
+        error_msg = f"Block of type {block['type']} is not supported."
+        raise ValueError(error_msg)
+
+    return formatted_block
+
+
 # v1 / Chat Completions
 def _convert_to_v1_from_chat_completions(
     message: AIMessage,
@@ -57,7 +164,7 @@ def _convert_to_v1_from_chat_completions_input(
     Returns:
         Updated list with OpenAI blocks converted to v1 format.
     """
-    from langchain_core.messages import content as types
+    from langchain_core.messages import content as types  # noqa: PLC0415
 
     converted_blocks = []
     unpacked_blocks: list[dict[str, Any]] = [
@@ -71,7 +178,7 @@ def _convert_to_v1_from_chat_completions_input(
             "image_url",
             "input_audio",
             "file",
-        } and _is_openai_data_block(block):
+        } and is_openai_data_block(block):
             converted_block = _convert_openai_format_to_data_block(block)
             # If conversion succeeded, use it; otherwise keep as non_standard
             if (
@@ -153,7 +260,7 @@ _FUNCTION_CALL_IDS_MAP_KEY = "__openai_function_call_ids__"
 
 def _convert_from_v03_ai_message(message: AIMessage) -> AIMessage:
     """Convert v0 AIMessage into ``output_version="responses/v1"`` format."""
-    from langchain_core.messages import AIMessageChunk
+    from langchain_core.messages import AIMessageChunk  # noqa: PLC0415
 
     # Only update ChatOpenAI v0.3 AIMessages
     is_chatopenai_v03 = (
@@ -288,6 +395,139 @@ def _convert_from_v03_ai_message(message: AIMessage) -> AIMessage:
     )
 
 
+def _convert_openai_format_to_data_block(
+    block: dict,
+) -> Union[types.ContentBlock, dict[Any, Any]]:
+    """Convert OpenAI image/audio/file content block to respective v1 multimodal block.
+
+    We expect that the incoming block is verified to be in OpenAI Chat Completions
+    format.
+
+    If parsing fails, passes block through unchanged.
+
+    Mappings (Chat Completions to LangChain v1):
+    - Image -> `ImageContentBlock`
+    - Audio -> `AudioContentBlock`
+    - File -> `FileContentBlock`
+
+    """
+
+    # Extract extra keys to put them in `extras`
+    def _extract_extras(block_dict: dict, known_keys: set[str]) -> dict[str, Any]:
+        """Extract unknown keys from block to preserve as extras."""
+        return {k: v for k, v in block_dict.items() if k not in known_keys}
+
+    # base64-style image block
+    if (block["type"] == "image_url") and (
+        parsed := _parse_data_uri(block["image_url"]["url"])
+    ):
+        known_keys = {"type", "image_url"}
+        extras = _extract_extras(block, known_keys)
+
+        # Also extract extras from nested image_url dict
+        image_url_known_keys = {"url"}
+        image_url_extras = _extract_extras(block["image_url"], image_url_known_keys)
+
+        # Merge extras
+        all_extras = {**extras}
+        for key, value in image_url_extras.items():
+            if key == "detail":  # Don't rename
+                all_extras["detail"] = value
+            else:
+                all_extras[f"image_url_{key}"] = value
+
+        return types.create_image_block(
+            # Even though this is labeled as `url`, it can be base64-encoded
+            base64=parsed["data"],
+            mime_type=parsed["mime_type"],
+            **all_extras,
+        )
+
+    # url-style image block
+    if (block["type"] == "image_url") and isinstance(
+        block["image_url"].get("url"), str
+    ):
+        known_keys = {"type", "image_url"}
+        extras = _extract_extras(block, known_keys)
+
+        image_url_known_keys = {"url"}
+        image_url_extras = _extract_extras(block["image_url"], image_url_known_keys)
+
+        all_extras = {**extras}
+        for key, value in image_url_extras.items():
+            if key == "detail":  # Don't rename
+                all_extras["detail"] = value
+            else:
+                all_extras[f"image_url_{key}"] = value
+
+        return types.create_image_block(
+            url=block["image_url"]["url"],
+            **all_extras,
+        )
+
+    # base64-style audio block
+    # audio is only represented via raw data, no url or ID option
+    if block["type"] == "input_audio":
+        known_keys = {"type", "input_audio"}
+        extras = _extract_extras(block, known_keys)
+
+        # Also extract extras from nested audio dict
+        audio_known_keys = {"data", "format"}
+        audio_extras = _extract_extras(block["input_audio"], audio_known_keys)
+
+        all_extras = {**extras}
+        for key, value in audio_extras.items():
+            all_extras[f"audio_{key}"] = value
+
+        return types.create_audio_block(
+            base64=block["input_audio"]["data"],
+            mime_type=f"audio/{block['input_audio']['format']}",
+            **all_extras,
+        )
+
+    # id-style file block
+    if block.get("type") == "file" and "file_id" in block.get("file", {}):
+        known_keys = {"type", "file"}
+        extras = _extract_extras(block, known_keys)
+
+        file_known_keys = {"file_id"}
+        file_extras = _extract_extras(block["file"], file_known_keys)
+
+        all_extras = {**extras}
+        for key, value in file_extras.items():
+            all_extras[f"file_{key}"] = value
+
+        return types.create_file_block(
+            file_id=block["file"]["file_id"],
+            **all_extras,
+        )
+
+    # base64-style file block
+    if (block["type"] == "file") and (
+        parsed := _parse_data_uri(block["file"]["file_data"])
+    ):
+        known_keys = {"type", "file"}
+        extras = _extract_extras(block, known_keys)
+
+        file_known_keys = {"file_data", "filename"}
+        file_extras = _extract_extras(block["file"], file_known_keys)
+
+        all_extras = {**extras}
+        for key, value in file_extras.items():
+            all_extras[f"file_{key}"] = value
+
+        filename = block["file"].get("filename")
+        return types.create_file_block(
+            base64=parsed["data"],
+            mime_type="application/pdf",
+            filename=filename,
+            **all_extras,
+        )
+
+    # Escape hatch
+    return block
+
+
 # v1 / Responses
 def _convert_annotation_to_v1(annotation: dict[str, Any]) -> types.Annotation:
     annotation_type = annotation.get("type")
@@ -438,7 +678,7 @@ def _convert_to_v1_from_responses(message: AIMessage) -> list[types.ContentBlock
                 ] = None
                 call_id = block.get("call_id", "")
 
-                from langchain_core.messages import AIMessageChunk
+                from langchain_core.messages import AIMessageChunk  # noqa: PLC0415
 
                 if (
                     isinstance(message, AIMessageChunk)
@@ -578,7 +818,9 @@ def _register_openai_translator() -> None:
 
     Run automatically when the module is imported.
     """
-    from langchain_core.messages.block_translators import register_translator
+    from langchain_core.messages.block_translators import (  # noqa: PLC0415
+        register_translator,
+    )
 
     register_translator("openai", translate_content, translate_content_chunk)