feat: add file support for more LLM API Flavors

Author: ionut-mihalache-uipath

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "uipath-langchain"
-version = "0.4.9"
+version = "0.4.10"
 description = "Python SDK that enables developers to build and deploy LangGraph agents to the UiPath Cloud Platform"
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.11"

src/uipath_langchain/agent/react/file_type_handler.py

@@ -1,11 +1,13 @@
 """LLM node for ReAct Agent graph."""
 
-from typing import Literal, Sequence
+from typing import Any, Sequence
 
 from langchain_core.language_models import BaseChatModel
 from langchain_core.messages import AIMessage, AnyMessage
 from langchain_core.tools import BaseTool
 
+from uipath_langchain.chat.types import APIFlavor
+
 from .constants import MAX_CONSECUTIVE_THINKING_MESSAGES
 from .types import AgentGraphState
 from .utils import count_consecutive_thinking_messages
@@ -21,15 +23,22 @@
 
 def _get_required_tool_choice_by_model(
     model: BaseChatModel,
-) -> Literal["required", "any"]:
+) -> str | dict[str, Any]:
     """Get the appropriate tool_choice value to enforce tool usage based on model type.
 
-    "required" - OpenAI compatible required tool_choice value
-    "any" - Vertex and Bedrock parameter for required tool_choice value
+    Returns:
+        - "required" for OpenAI compatible models
+        - "any" for Bedrock Converse and Vertex models (string format)
+        - {"type": "any"} for Bedrock Invoke API (dict format required)
     """
     model_class_name = model.__class__.__name__
     if model_class_name in OPENAI_COMPATIBLE_CHAT_MODELS:
         return "required"
+
+    api_flavor = getattr(model, "api_flavor", None)
+    if api_flavor == APIFlavor.AWS_BEDROCK_INVOKE:
+        return {"type": "any"}
+
     return "any"
 
 

src/uipath_langchain/agent/react/llm_node.py

@@ -6,7 +6,7 @@
 from langchain_core.language_models import BaseChatModel
 from langchain_core.messages import AIMessage, AnyMessage, HumanMessage
 
-from .file_type_handler import build_message_content_part_from_data
+from uipath_langchain.llm import get_content_builder
 
 
 @dataclass
@@ -18,29 +18,24 @@ class FileInfo:
     mime_type: str
 
 
-def _get_model_name(model: BaseChatModel) -> str:
-    """Extract model name from a BaseChatModel instance."""
-    for attr in ["model_name", "_model_name", "model", "model_id"]:
-        value = getattr(model, attr, None)
-        if value and isinstance(value, str):
-            return value
-    raise ValueError(f"Model name not found in model {model}")
-
-
-async def create_part_for_file(
+async def build_file_content_part(
     file_info: FileInfo,
     model: BaseChatModel,
 ) -> dict[str, Any]:
-    """Create a provider-specific message content part for a file attachment.
+    """Build a provider-specific message content part for a file attachment.
+
+    Args:
+        file_info: File URL, name, and MIME type.
+        model: The LLM model instance (must have llm_provider and api_flavor attributes).
 
-    Downloads the file from file_info.url and formats it for the model's provider.
+    Returns:
+        Provider-specific content part dictionary.
     """
-    model_name = _get_model_name(model)
-    return await build_message_content_part_from_data(
+    builder = get_content_builder(model)
+    return await builder.build_file_content_part(
         url=file_info.url,
         filename=file_info.name,
         mime_type=file_info.mime_type,
-        model=model_name,
     )
 
 
@@ -64,7 +59,7 @@ async def llm_call_with_files(
 
     content_parts: list[str | dict[Any, Any]] = []
     for file_info in files:
-        content_part = await create_part_for_file(file_info, model)
+        content_part = await build_file_content_part(file_info, model)
         content_parts.append(content_part)
 
     file_message = HumanMessage(content=content_parts)

src/uipath_langchain/agent/react/llm_with_files.py

@@ -29,6 +29,10 @@ def __getattr__(name):
         from . import supported_models
 
         return getattr(supported_models, name)
+    if name in ("LLMProvider", "APIFlavor"):
+        from . import types
+
+        return getattr(types, name)
     raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
 
 
@@ -39,4 +43,6 @@ def __getattr__(name):
     "OpenAIModels",
     "BedrockModels",
     "GeminiModels",
+    "LLMProvider",
+    "APIFlavor",
 ]

src/uipath_langchain/chat/__init__.py

@@ -5,6 +5,7 @@
 from uipath.utils import EndpointManager
 
 from .supported_models import BedrockModels
+from .types import APIFlavor, LLMProvider
 
 logger = logging.getLogger(__name__)
 
@@ -120,6 +121,9 @@ def _modify_request(self, request, **kwargs):
 
 
 class UiPathChatBedrockConverse(ChatBedrockConverse):
+    llm_provider: LLMProvider = LLMProvider.BEDROCK
+    api_flavor: APIFlavor = APIFlavor.AWS_BEDROCK_CONVERSE
+
     def __init__(
         self,
         org_id: Optional[str] = None,
@@ -162,6 +166,9 @@ def __init__(
 
 
 class UiPathChatBedrock(ChatBedrock):
+    llm_provider: LLMProvider = LLMProvider.BEDROCK
+    api_flavor: APIFlavor = APIFlavor.AWS_BEDROCK_INVOKE
+
     def __init__(
         self,
         org_id: Optional[str] = None,

src/uipath_langchain/chat/bedrock.py

@@ -21,12 +21,17 @@
 
 from uipath_langchain._utils._request_mixin import UiPathRequestMixin
 
+from .types import APIFlavor, LLMProvider
+
 logger = logging.getLogger(__name__)
 
 
 class UiPathAzureChatOpenAI(UiPathRequestMixin, AzureChatOpenAI):
     """Custom LLM connector for LangChain integration with UiPath."""
 
+    llm_provider: LLMProvider = LLMProvider.OPENAI
+    api_flavor: APIFlavor = APIFlavor.OPENAI_COMPLETIONS
+
     def _generate(
         self,
         messages: list[BaseMessage],
@@ -169,6 +174,9 @@ def endpoint(self) -> str:
 class UiPathChat(UiPathRequestMixin, AzureChatOpenAI):
     """Custom LLM connector for LangChain integration with UiPath Normalized."""
 
+    llm_provider: LLMProvider = LLMProvider.OPENAI
+    api_flavor: APIFlavor = APIFlavor.OPENAI_COMPLETIONS
+
     def _create_chat_result(
         self,
         response: Union[dict[str, Any], BaseModel],