From 3238fa087072449eb077d467b7eecf1af127cd10 Mon Sep 17 00:00:00 2001 From: Nuno Campos Date: Tue, 30 Jul 2024 15:50:18 -0700 Subject: [PATCH] Add test for drawing lance example --- libs/langgraph/poetry.lock | 6 +- .../tests/__snapshots__/test_pregel.ambr | 247 +++++++++++++++++- libs/langgraph/tests/test_pregel.py | 127 +++++++++ 3 files changed, 375 insertions(+), 5 deletions(-) diff --git a/libs/langgraph/poetry.lock b/libs/langgraph/poetry.lock index 0b7a1755f..f7173efbe 100644 --- a/libs/langgraph/poetry.lock +++ b/libs/langgraph/poetry.lock @@ -1760,13 +1760,13 @@ langchain-core = ">=0.2.2rc1,<0.3" [[package]] name = "langchain-core" -version = "0.2.22" +version = "0.2.25" description = "Building applications with LLMs through composability" optional = false python-versions = "<4.0,>=3.8.1" files = [ - {file = "langchain_core-0.2.22-py3-none-any.whl", hash = "sha256:7731a86440c0958b3186c003fb9b26b2d5a682a6344bda7bfb9174e2898f8b43"}, - {file = "langchain_core-0.2.22.tar.gz", hash = "sha256:582d6f929a43b830139444e4124123cd415331ad62f25757b1406252958cdcac"}, + {file = "langchain_core-0.2.25-py3-none-any.whl", hash = "sha256:03d61b2a7f4b5f98df248c1b1f0ccd95c9d5ef2269e174133724365cd2a7ee1e"}, + {file = "langchain_core-0.2.25.tar.gz", hash = "sha256:e64106a7d0e37e4d35b767f79e6c62b56e825f08f9e8cc4368bcea9955257a7e"}, ] [package.dependencies] diff --git a/libs/langgraph/tests/__snapshots__/test_pregel.ambr b/libs/langgraph/tests/__snapshots__/test_pregel.ambr index 3c0b72c15..9295abf6f 100644 --- a/libs/langgraph/tests/__snapshots__/test_pregel.ambr +++ b/libs/langgraph/tests/__snapshots__/test_pregel.ambr @@ -855,10 +855,10 @@ ''' # --- # name: test_message_graph - '{"title": "LangGraphInput", "type": "array", "items": {"anyOf": [{"$ref": "#/definitions/AIMessage"}, {"$ref": "#/definitions/HumanMessage"}, {"$ref": "#/definitions/ChatMessage"}, {"$ref": "#/definitions/SystemMessage"}, {"$ref": "#/definitions/FunctionMessage"}, {"$ref": "#/definitions/ToolMessage"}]}, "definitions": {"ToolCall": {"title": "ToolCall", "type": "object", "properties": {"name": {"title": "Name", "type": "string"}, "args": {"title": "Args", "type": "object"}, "id": {"title": "Id", "type": "string"}, "type": {"title": "Type", "enum": ["tool_call"], "type": "string"}}, "required": ["name", "args", "id"]}, "InvalidToolCall": {"title": "InvalidToolCall", "type": "object", "properties": {"name": {"title": "Name", "type": "string"}, "args": {"title": "Args", "type": "string"}, "id": {"title": "Id", "type": "string"}, "error": {"title": "Error", "type": "string"}, "type": {"title": "Type", "enum": ["invalid_tool_call"], "type": "string"}}, "required": ["name", "args", "id", "error"]}, "UsageMetadata": {"title": "UsageMetadata", "type": "object", "properties": {"input_tokens": {"title": "Input Tokens", "type": "integer"}, "output_tokens": {"title": "Output Tokens", "type": "integer"}, "total_tokens": {"title": "Total Tokens", "type": "integer"}}, "required": ["input_tokens", "output_tokens", "total_tokens"]}, "AIMessage": {"title": "AIMessage", "description": "Message from an AI.\\n\\nAIMessage is returned from a chat model as a response to a prompt.\\n\\nThis message represents the output of the model and consists of both\\nthe raw output as returned by the model together standardized fields\\n(e.g., tool calls, usage metadata) added by the LangChain framework.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "ai", "enum": ["ai"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "example": {"title": "Example", "default": false, "type": "boolean"}, "tool_calls": {"title": "Tool Calls", "default": [], "type": "array", "items": {"$ref": "#/definitions/ToolCall"}}, "invalid_tool_calls": {"title": "Invalid Tool Calls", "default": [], "type": "array", "items": {"$ref": "#/definitions/InvalidToolCall"}}, "usage_metadata": {"$ref": "#/definitions/UsageMetadata"}}, "required": ["content"]}, "HumanMessage": {"title": "HumanMessage", "description": "Message from a human.\\n\\nHumanMessages are messages that are passed in from a human to the model.\\n\\nExample:\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import HumanMessage, SystemMessage\\n\\n messages = [\\n SystemMessage(\\n content=\\"You are a helpful assistant! Your name is Bob.\\"\\n ),\\n HumanMessage(\\n content=\\"What is your name?\\"\\n )\\n ]\\n\\n # Instantiate a chat model and invoke it with the messages\\n model = ...\\n print(model.invoke(messages))", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "human", "enum": ["human"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "example": {"title": "Example", "default": false, "type": "boolean"}}, "required": ["content"]}, "ChatMessage": {"title": "ChatMessage", "description": "Message that can be assigned an arbitrary speaker (i.e. role).", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "chat", "enum": ["chat"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "role": {"title": "Role", "type": "string"}}, "required": ["content", "role"]}, "SystemMessage": {"title": "SystemMessage", "description": "Message for priming AI behavior.\\n\\nThe system message is usually passed in as the first of a sequence\\nof input messages.\\n\\nExample:\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import HumanMessage, SystemMessage\\n\\n messages = [\\n SystemMessage(\\n content=\\"You are a helpful assistant! Your name is Bob.\\"\\n ),\\n HumanMessage(\\n content=\\"What is your name?\\"\\n )\\n ]\\n\\n # Define a chat model and invoke it with the messages\\n print(model.invoke(messages))", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "system", "enum": ["system"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}}, "required": ["content"]}, "FunctionMessage": {"title": "FunctionMessage", "description": "Message for passing the result of executing a tool back to a model.\\n\\nFunctionMessage are an older version of the ToolMessage schema, and\\ndo not contain the tool_call_id field.\\n\\nThe tool_call_id field is used to associate the tool call request with the\\ntool call response. This is useful in situations where a chat model is able\\nto request multiple tool calls in parallel.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "function", "enum": ["function"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}}, "required": ["content", "name"]}, "ToolMessage": {"title": "ToolMessage", "description": "Message for passing the result of executing a tool back to a model.\\n\\nToolMessages contain the result of a tool invocation. Typically, the result\\nis encoded inside the `content` field.\\n\\nExample: A ToolMessage representing a result of 42 from a tool call with id\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import ToolMessage\\n\\n ToolMessage(content=\'42\', tool_call_id=\'call_Jja7J89XsjrOLA5r!MEOW!SL\')\\n\\n\\nExample: A ToolMessage where only part of the tool output is sent to the model\\n and the full output is passed in to artifact.\\n\\n .. versionadded:: 0.2.17\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import ToolMessage\\n\\n tool_output = {\\n \\"stdout\\": \\"From the graph we can see that the correlation between x and y is ...\\",\\n \\"stderr\\": None,\\n \\"artifacts\\": {\\"type\\": \\"image\\", \\"base64_data\\": \\"/9j/4gIcSU...\\"},\\n }\\n\\n ToolMessage(\\n content=tool_output[\\"stdout\\"],\\n artifact=tool_output,\\n tool_call_id=\'call_Jja7J89XsjrOLA5r!MEOW!SL\',\\n )\\n\\nThe tool_call_id field is used to associate the tool call request with the\\ntool call response. This is useful in situations where a chat model is able\\nto request multiple tool calls in parallel.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "tool", "enum": ["tool"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "tool_call_id": {"title": "Tool Call Id", "type": "string"}, "artifact": {"title": "Artifact"}}, "required": ["content", "tool_call_id"]}}}' + '{"title": "LangGraphInput", "type": "array", "items": {"anyOf": [{"$ref": "#/definitions/AIMessage"}, {"$ref": "#/definitions/HumanMessage"}, {"$ref": "#/definitions/ChatMessage"}, {"$ref": "#/definitions/SystemMessage"}, {"$ref": "#/definitions/FunctionMessage"}, {"$ref": "#/definitions/ToolMessage"}]}, "definitions": {"ToolCall": {"title": "ToolCall", "type": "object", "properties": {"name": {"title": "Name", "type": "string"}, "args": {"title": "Args", "type": "object"}, "id": {"title": "Id", "type": "string"}, "type": {"title": "Type", "enum": ["tool_call"], "type": "string"}}, "required": ["name", "args", "id"]}, "InvalidToolCall": {"title": "InvalidToolCall", "type": "object", "properties": {"name": {"title": "Name", "type": "string"}, "args": {"title": "Args", "type": "string"}, "id": {"title": "Id", "type": "string"}, "error": {"title": "Error", "type": "string"}, "type": {"title": "Type", "enum": ["invalid_tool_call"], "type": "string"}}, "required": ["name", "args", "id", "error"]}, "UsageMetadata": {"title": "UsageMetadata", "type": "object", "properties": {"input_tokens": {"title": "Input Tokens", "type": "integer"}, "output_tokens": {"title": "Output Tokens", "type": "integer"}, "total_tokens": {"title": "Total Tokens", "type": "integer"}}, "required": ["input_tokens", "output_tokens", "total_tokens"]}, "AIMessage": {"title": "AIMessage", "description": "Message from an AI.\\n\\nAIMessage is returned from a chat model as a response to a prompt.\\n\\nThis message represents the output of the model and consists of both\\nthe raw output as returned by the model together standardized fields\\n(e.g., tool calls, usage metadata) added by the LangChain framework.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "ai", "enum": ["ai"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "example": {"title": "Example", "default": false, "type": "boolean"}, "tool_calls": {"title": "Tool Calls", "default": [], "type": "array", "items": {"$ref": "#/definitions/ToolCall"}}, "invalid_tool_calls": {"title": "Invalid Tool Calls", "default": [], "type": "array", "items": {"$ref": "#/definitions/InvalidToolCall"}}, "usage_metadata": {"$ref": "#/definitions/UsageMetadata"}}, "required": ["content"]}, "HumanMessage": {"title": "HumanMessage", "description": "Message from a human.\\n\\nHumanMessages are messages that are passed in from a human to the model.\\n\\nExample:\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import HumanMessage, SystemMessage\\n\\n messages = [\\n SystemMessage(\\n content=\\"You are a helpful assistant! Your name is Bob.\\"\\n ),\\n HumanMessage(\\n content=\\"What is your name?\\"\\n )\\n ]\\n\\n # Instantiate a chat model and invoke it with the messages\\n model = ...\\n print(model.invoke(messages))", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "human", "enum": ["human"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "example": {"title": "Example", "default": false, "type": "boolean"}}, "required": ["content"]}, "ChatMessage": {"title": "ChatMessage", "description": "Message that can be assigned an arbitrary speaker (i.e. role).", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "chat", "enum": ["chat"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "role": {"title": "Role", "type": "string"}}, "required": ["content", "role"]}, "SystemMessage": {"title": "SystemMessage", "description": "Message for priming AI behavior.\\n\\nThe system message is usually passed in as the first of a sequence\\nof input messages.\\n\\nExample:\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import HumanMessage, SystemMessage\\n\\n messages = [\\n SystemMessage(\\n content=\\"You are a helpful assistant! Your name is Bob.\\"\\n ),\\n HumanMessage(\\n content=\\"What is your name?\\"\\n )\\n ]\\n\\n # Define a chat model and invoke it with the messages\\n print(model.invoke(messages))", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "system", "enum": ["system"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}}, "required": ["content"]}, "FunctionMessage": {"title": "FunctionMessage", "description": "Message for passing the result of executing a tool back to a model.\\n\\nFunctionMessage are an older version of the ToolMessage schema, and\\ndo not contain the tool_call_id field.\\n\\nThe tool_call_id field is used to associate the tool call request with the\\ntool call response. This is useful in situations where a chat model is able\\nto request multiple tool calls in parallel.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "function", "enum": ["function"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}}, "required": ["content", "name"]}, "ToolMessage": {"title": "ToolMessage", "description": "Message for passing the result of executing a tool back to a model.\\n\\nToolMessages contain the result of a tool invocation. Typically, the result\\nis encoded inside the `content` field.\\n\\nExample: A ToolMessage representing a result of 42 from a tool call with id\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import ToolMessage\\n\\n ToolMessage(content=\'42\', tool_call_id=\'call_Jja7J89XsjrOLA5r!MEOW!SL\')\\n\\n\\nExample: A ToolMessage where only part of the tool output is sent to the model\\n and the full output is passed in to artifact.\\n\\n .. versionadded:: 0.2.17\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import ToolMessage\\n\\n tool_output = {\\n \\"stdout\\": \\"From the graph we can see that the correlation between x and y is ...\\",\\n \\"stderr\\": None,\\n \\"artifacts\\": {\\"type\\": \\"image\\", \\"base64_data\\": \\"/9j/4gIcSU...\\"},\\n }\\n\\n ToolMessage(\\n content=tool_output[\\"stdout\\"],\\n artifact=tool_output,\\n tool_call_id=\'call_Jja7J89XsjrOLA5r!MEOW!SL\',\\n )\\n\\nThe tool_call_id field is used to associate the tool call request with the\\ntool call response. This is useful in situations where a chat model is able\\nto request multiple tool calls in parallel.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "tool", "enum": ["tool"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "tool_call_id": {"title": "Tool Call Id", "type": "string"}, "artifact": {"title": "Artifact"}, "status": {"title": "Status", "default": "success", "enum": ["success", "error"], "type": "string"}}, "required": ["content", "tool_call_id"]}}}' # --- # name: test_message_graph.1 - '{"title": "LangGraphOutput", "type": "array", "items": {"anyOf": [{"$ref": "#/definitions/AIMessage"}, {"$ref": "#/definitions/HumanMessage"}, {"$ref": "#/definitions/ChatMessage"}, {"$ref": "#/definitions/SystemMessage"}, {"$ref": "#/definitions/FunctionMessage"}, {"$ref": "#/definitions/ToolMessage"}]}, "definitions": {"ToolCall": {"title": "ToolCall", "type": "object", "properties": {"name": {"title": "Name", "type": "string"}, "args": {"title": "Args", "type": "object"}, "id": {"title": "Id", "type": "string"}, "type": {"title": "Type", "enum": ["tool_call"], "type": "string"}}, "required": ["name", "args", "id"]}, "InvalidToolCall": {"title": "InvalidToolCall", "type": "object", "properties": {"name": {"title": "Name", "type": "string"}, "args": {"title": "Args", "type": "string"}, "id": {"title": "Id", "type": "string"}, "error": {"title": "Error", "type": "string"}, "type": {"title": "Type", "enum": ["invalid_tool_call"], "type": "string"}}, "required": ["name", "args", "id", "error"]}, "UsageMetadata": {"title": "UsageMetadata", "type": "object", "properties": {"input_tokens": {"title": "Input Tokens", "type": "integer"}, "output_tokens": {"title": "Output Tokens", "type": "integer"}, "total_tokens": {"title": "Total Tokens", "type": "integer"}}, "required": ["input_tokens", "output_tokens", "total_tokens"]}, "AIMessage": {"title": "AIMessage", "description": "Message from an AI.\\n\\nAIMessage is returned from a chat model as a response to a prompt.\\n\\nThis message represents the output of the model and consists of both\\nthe raw output as returned by the model together standardized fields\\n(e.g., tool calls, usage metadata) added by the LangChain framework.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "ai", "enum": ["ai"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "example": {"title": "Example", "default": false, "type": "boolean"}, "tool_calls": {"title": "Tool Calls", "default": [], "type": "array", "items": {"$ref": "#/definitions/ToolCall"}}, "invalid_tool_calls": {"title": "Invalid Tool Calls", "default": [], "type": "array", "items": {"$ref": "#/definitions/InvalidToolCall"}}, "usage_metadata": {"$ref": "#/definitions/UsageMetadata"}}, "required": ["content"]}, "HumanMessage": {"title": "HumanMessage", "description": "Message from a human.\\n\\nHumanMessages are messages that are passed in from a human to the model.\\n\\nExample:\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import HumanMessage, SystemMessage\\n\\n messages = [\\n SystemMessage(\\n content=\\"You are a helpful assistant! Your name is Bob.\\"\\n ),\\n HumanMessage(\\n content=\\"What is your name?\\"\\n )\\n ]\\n\\n # Instantiate a chat model and invoke it with the messages\\n model = ...\\n print(model.invoke(messages))", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "human", "enum": ["human"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "example": {"title": "Example", "default": false, "type": "boolean"}}, "required": ["content"]}, "ChatMessage": {"title": "ChatMessage", "description": "Message that can be assigned an arbitrary speaker (i.e. role).", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "chat", "enum": ["chat"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "role": {"title": "Role", "type": "string"}}, "required": ["content", "role"]}, "SystemMessage": {"title": "SystemMessage", "description": "Message for priming AI behavior.\\n\\nThe system message is usually passed in as the first of a sequence\\nof input messages.\\n\\nExample:\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import HumanMessage, SystemMessage\\n\\n messages = [\\n SystemMessage(\\n content=\\"You are a helpful assistant! Your name is Bob.\\"\\n ),\\n HumanMessage(\\n content=\\"What is your name?\\"\\n )\\n ]\\n\\n # Define a chat model and invoke it with the messages\\n print(model.invoke(messages))", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "system", "enum": ["system"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}}, "required": ["content"]}, "FunctionMessage": {"title": "FunctionMessage", "description": "Message for passing the result of executing a tool back to a model.\\n\\nFunctionMessage are an older version of the ToolMessage schema, and\\ndo not contain the tool_call_id field.\\n\\nThe tool_call_id field is used to associate the tool call request with the\\ntool call response. This is useful in situations where a chat model is able\\nto request multiple tool calls in parallel.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "function", "enum": ["function"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}}, "required": ["content", "name"]}, "ToolMessage": {"title": "ToolMessage", "description": "Message for passing the result of executing a tool back to a model.\\n\\nToolMessages contain the result of a tool invocation. Typically, the result\\nis encoded inside the `content` field.\\n\\nExample: A ToolMessage representing a result of 42 from a tool call with id\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import ToolMessage\\n\\n ToolMessage(content=\'42\', tool_call_id=\'call_Jja7J89XsjrOLA5r!MEOW!SL\')\\n\\n\\nExample: A ToolMessage where only part of the tool output is sent to the model\\n and the full output is passed in to artifact.\\n\\n .. versionadded:: 0.2.17\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import ToolMessage\\n\\n tool_output = {\\n \\"stdout\\": \\"From the graph we can see that the correlation between x and y is ...\\",\\n \\"stderr\\": None,\\n \\"artifacts\\": {\\"type\\": \\"image\\", \\"base64_data\\": \\"/9j/4gIcSU...\\"},\\n }\\n\\n ToolMessage(\\n content=tool_output[\\"stdout\\"],\\n artifact=tool_output,\\n tool_call_id=\'call_Jja7J89XsjrOLA5r!MEOW!SL\',\\n )\\n\\nThe tool_call_id field is used to associate the tool call request with the\\ntool call response. This is useful in situations where a chat model is able\\nto request multiple tool calls in parallel.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "tool", "enum": ["tool"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "tool_call_id": {"title": "Tool Call Id", "type": "string"}, "artifact": {"title": "Artifact"}}, "required": ["content", "tool_call_id"]}}}' + '{"title": "LangGraphOutput", "type": "array", "items": {"anyOf": [{"$ref": "#/definitions/AIMessage"}, {"$ref": "#/definitions/HumanMessage"}, {"$ref": "#/definitions/ChatMessage"}, {"$ref": "#/definitions/SystemMessage"}, {"$ref": "#/definitions/FunctionMessage"}, {"$ref": "#/definitions/ToolMessage"}]}, "definitions": {"ToolCall": {"title": "ToolCall", "type": "object", "properties": {"name": {"title": "Name", "type": "string"}, "args": {"title": "Args", "type": "object"}, "id": {"title": "Id", "type": "string"}, "type": {"title": "Type", "enum": ["tool_call"], "type": "string"}}, "required": ["name", "args", "id"]}, "InvalidToolCall": {"title": "InvalidToolCall", "type": "object", "properties": {"name": {"title": "Name", "type": "string"}, "args": {"title": "Args", "type": "string"}, "id": {"title": "Id", "type": "string"}, "error": {"title": "Error", "type": "string"}, "type": {"title": "Type", "enum": ["invalid_tool_call"], "type": "string"}}, "required": ["name", "args", "id", "error"]}, "UsageMetadata": {"title": "UsageMetadata", "type": "object", "properties": {"input_tokens": {"title": "Input Tokens", "type": "integer"}, "output_tokens": {"title": "Output Tokens", "type": "integer"}, "total_tokens": {"title": "Total Tokens", "type": "integer"}}, "required": ["input_tokens", "output_tokens", "total_tokens"]}, "AIMessage": {"title": "AIMessage", "description": "Message from an AI.\\n\\nAIMessage is returned from a chat model as a response to a prompt.\\n\\nThis message represents the output of the model and consists of both\\nthe raw output as returned by the model together standardized fields\\n(e.g., tool calls, usage metadata) added by the LangChain framework.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "ai", "enum": ["ai"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "example": {"title": "Example", "default": false, "type": "boolean"}, "tool_calls": {"title": "Tool Calls", "default": [], "type": "array", "items": {"$ref": "#/definitions/ToolCall"}}, "invalid_tool_calls": {"title": "Invalid Tool Calls", "default": [], "type": "array", "items": {"$ref": "#/definitions/InvalidToolCall"}}, "usage_metadata": {"$ref": "#/definitions/UsageMetadata"}}, "required": ["content"]}, "HumanMessage": {"title": "HumanMessage", "description": "Message from a human.\\n\\nHumanMessages are messages that are passed in from a human to the model.\\n\\nExample:\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import HumanMessage, SystemMessage\\n\\n messages = [\\n SystemMessage(\\n content=\\"You are a helpful assistant! Your name is Bob.\\"\\n ),\\n HumanMessage(\\n content=\\"What is your name?\\"\\n )\\n ]\\n\\n # Instantiate a chat model and invoke it with the messages\\n model = ...\\n print(model.invoke(messages))", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "human", "enum": ["human"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "example": {"title": "Example", "default": false, "type": "boolean"}}, "required": ["content"]}, "ChatMessage": {"title": "ChatMessage", "description": "Message that can be assigned an arbitrary speaker (i.e. role).", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "chat", "enum": ["chat"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "role": {"title": "Role", "type": "string"}}, "required": ["content", "role"]}, "SystemMessage": {"title": "SystemMessage", "description": "Message for priming AI behavior.\\n\\nThe system message is usually passed in as the first of a sequence\\nof input messages.\\n\\nExample:\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import HumanMessage, SystemMessage\\n\\n messages = [\\n SystemMessage(\\n content=\\"You are a helpful assistant! Your name is Bob.\\"\\n ),\\n HumanMessage(\\n content=\\"What is your name?\\"\\n )\\n ]\\n\\n # Define a chat model and invoke it with the messages\\n print(model.invoke(messages))", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "system", "enum": ["system"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}}, "required": ["content"]}, "FunctionMessage": {"title": "FunctionMessage", "description": "Message for passing the result of executing a tool back to a model.\\n\\nFunctionMessage are an older version of the ToolMessage schema, and\\ndo not contain the tool_call_id field.\\n\\nThe tool_call_id field is used to associate the tool call request with the\\ntool call response. This is useful in situations where a chat model is able\\nto request multiple tool calls in parallel.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "function", "enum": ["function"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}}, "required": ["content", "name"]}, "ToolMessage": {"title": "ToolMessage", "description": "Message for passing the result of executing a tool back to a model.\\n\\nToolMessages contain the result of a tool invocation. Typically, the result\\nis encoded inside the `content` field.\\n\\nExample: A ToolMessage representing a result of 42 from a tool call with id\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import ToolMessage\\n\\n ToolMessage(content=\'42\', tool_call_id=\'call_Jja7J89XsjrOLA5r!MEOW!SL\')\\n\\n\\nExample: A ToolMessage where only part of the tool output is sent to the model\\n and the full output is passed in to artifact.\\n\\n .. versionadded:: 0.2.17\\n\\n .. code-block:: python\\n\\n from langchain_core.messages import ToolMessage\\n\\n tool_output = {\\n \\"stdout\\": \\"From the graph we can see that the correlation between x and y is ...\\",\\n \\"stderr\\": None,\\n \\"artifacts\\": {\\"type\\": \\"image\\", \\"base64_data\\": \\"/9j/4gIcSU...\\"},\\n }\\n\\n ToolMessage(\\n content=tool_output[\\"stdout\\"],\\n artifact=tool_output,\\n tool_call_id=\'call_Jja7J89XsjrOLA5r!MEOW!SL\',\\n )\\n\\nThe tool_call_id field is used to associate the tool call request with the\\ntool call response. This is useful in situations where a chat model is able\\nto request multiple tool calls in parallel.", "type": "object", "properties": {"content": {"title": "Content", "anyOf": [{"type": "string"}, {"type": "array", "items": {"anyOf": [{"type": "string"}, {"type": "object"}]}}]}, "additional_kwargs": {"title": "Additional Kwargs", "type": "object"}, "response_metadata": {"title": "Response Metadata", "type": "object"}, "type": {"title": "Type", "default": "tool", "enum": ["tool"], "type": "string"}, "name": {"title": "Name", "type": "string"}, "id": {"title": "Id", "type": "string"}, "tool_call_id": {"title": "Tool Call Id", "type": "string"}, "artifact": {"title": "Artifact"}, "status": {"title": "Status", "default": "success", "enum": ["success", "error"], "type": "string"}}, "required": ["content", "tool_call_id"]}}}' # --- # name: test_message_graph.2 ''' @@ -1324,3 +1324,246 @@ # name: test_state_graph_w_config '{"title": "LangGraphConfig", "type": "object", "properties": {"configurable": {"$ref": "#/definitions/Configurable"}}, "definitions": {"Configurable": {"title": "Configurable", "type": "object", "properties": {"tools": {"title": "Tools", "type": "array", "items": {"type": "string"}}}}}}' # --- +# name: test_xray_lance + dict({ + 'edges': list([ + dict({ + 'source': '__start__', + 'target': 'ask_question', + }), + dict({ + 'source': 'ask_question', + 'target': 'answer_question', + }), + dict({ + 'conditional': True, + 'source': 'answer_question', + 'target': 'ask_question', + }), + dict({ + 'conditional': True, + 'source': 'answer_question', + 'target': '__end__', + }), + ]), + 'nodes': list([ + dict({ + 'data': '__start__', + 'id': '__start__', + 'type': 'schema', + }), + dict({ + 'data': dict({ + 'id': list([ + 'langgraph', + 'utils', + 'RunnableCallable', + ]), + 'name': 'ask_question', + }), + 'id': 'ask_question', + 'type': 'runnable', + }), + dict({ + 'data': dict({ + 'id': list([ + 'langgraph', + 'utils', + 'RunnableCallable', + ]), + 'name': 'answer_question', + }), + 'id': 'answer_question', + 'type': 'runnable', + }), + dict({ + 'data': '__end__', + 'id': '__end__', + 'type': 'schema', + }), + ]), + }) +# --- +# name: test_xray_lance.1 + dict({ + 'edges': list([ + dict({ + 'source': '__start__', + 'target': 'generate_analysts', + }), + dict({ + 'source': 'conduct_interview', + 'target': 'generate_sections', + }), + dict({ + 'source': 'generate_sections', + 'target': '__end__', + }), + dict({ + 'conditional': True, + 'source': 'generate_analysts', + 'target': 'conduct_interview', + }), + ]), + 'nodes': list([ + dict({ + 'data': '__start__', + 'id': '__start__', + 'type': 'schema', + }), + dict({ + 'data': dict({ + 'id': list([ + 'langgraph', + 'utils', + 'RunnableCallable', + ]), + 'name': 'generate_analysts', + }), + 'id': 'generate_analysts', + 'type': 'runnable', + }), + dict({ + 'data': dict({ + 'id': list([ + 'langgraph', + 'graph', + 'state', + 'CompiledStateGraph', + ]), + 'name': 'conduct_interview', + }), + 'id': 'conduct_interview', + 'type': 'runnable', + }), + dict({ + 'data': dict({ + 'id': list([ + 'langgraph', + 'utils', + 'RunnableCallable', + ]), + 'name': 'generate_sections', + }), + 'id': 'generate_sections', + 'type': 'runnable', + }), + dict({ + 'data': '__end__', + 'id': '__end__', + 'type': 'schema', + }), + ]), + }) +# --- +# name: test_xray_lance.2 + dict({ + 'edges': list([ + dict({ + 'source': 'conduct_interview:__start__', + 'target': 'conduct_interview:ask_question', + }), + dict({ + 'source': 'conduct_interview:ask_question', + 'target': 'conduct_interview:answer_question', + }), + dict({ + 'conditional': True, + 'source': 'conduct_interview:answer_question', + 'target': 'conduct_interview:ask_question', + }), + dict({ + 'conditional': True, + 'source': 'conduct_interview:answer_question', + 'target': 'conduct_interview:__end__', + }), + dict({ + 'source': '__start__', + 'target': 'generate_analysts', + }), + dict({ + 'source': 'conduct_interview:__end__', + 'target': 'generate_sections', + }), + dict({ + 'source': 'generate_sections', + 'target': '__end__', + }), + dict({ + 'conditional': True, + 'source': 'generate_analysts', + 'target': 'conduct_interview:__start__', + }), + ]), + 'nodes': list([ + dict({ + 'data': '__start__', + 'id': '__start__', + 'type': 'schema', + }), + dict({ + 'data': dict({ + 'id': list([ + 'langgraph', + 'utils', + 'RunnableCallable', + ]), + 'name': 'generate_analysts', + }), + 'id': 'generate_analysts', + 'type': 'runnable', + }), + dict({ + 'data': 'conduct_interview:__start__', + 'id': 'conduct_interview:__start__', + 'type': 'schema', + }), + dict({ + 'data': dict({ + 'id': list([ + 'langgraph', + 'utils', + 'RunnableCallable', + ]), + 'name': 'conduct_interview:ask_question', + }), + 'id': 'conduct_interview:ask_question', + 'type': 'runnable', + }), + dict({ + 'data': dict({ + 'id': list([ + 'langgraph', + 'utils', + 'RunnableCallable', + ]), + 'name': 'conduct_interview:answer_question', + }), + 'id': 'conduct_interview:answer_question', + 'type': 'runnable', + }), + dict({ + 'data': 'conduct_interview:__end__', + 'id': 'conduct_interview:__end__', + 'type': 'schema', + }), + dict({ + 'data': dict({ + 'id': list([ + 'langgraph', + 'utils', + 'RunnableCallable', + ]), + 'name': 'generate_sections', + }), + 'id': 'generate_sections', + 'type': 'runnable', + }), + dict({ + 'data': '__end__', + 'id': '__end__', + 'type': 'schema', + }), + ]), + }) +# --- diff --git a/libs/langgraph/tests/test_pregel.py b/libs/langgraph/tests/test_pregel.py index 87a73647e..04a71bfa3 100644 --- a/libs/langgraph/tests/test_pregel.py +++ b/libs/langgraph/tests/test_pregel.py @@ -9097,3 +9097,130 @@ def test_remove_message_from_node(): output = app.invoke([HumanMessage(content="Hi")]) assert len(output) == 2 assert output[-1].content == "How can I help you?" + + +def test_xray_lance(snapshot: SnapshotAssertion): + from langchain_core.messages import AnyMessage, HumanMessage + from langchain_core.pydantic_v1 import BaseModel, Field + + class Analyst(BaseModel): + affiliation: str = Field( + description="Primary affiliation of the investment analyst.", + ) + name: str = Field( + description="Name of the investment analyst.", + pattern=r"^[a-zA-Z0-9_-]{1,64}$", + ) + role: str = Field( + description="Role of the investment analyst in the context of the topic.", + ) + description: str = Field( + description="Description of the investment analyst focus, concerns, and motives.", + ) + + @property + def persona(self) -> str: + return f"Name: {self.name}\nRole: {self.role}\nAffiliation: {self.affiliation}\nDescription: {self.description}\n" + + class Perspectives(BaseModel): + analysts: List[Analyst] = Field( + description="Comprehensive list of investment analysts with their roles and affiliations.", + ) + + class Section(BaseModel): + section_title: str = Field(..., title="Title of the section") + context: str = Field( + ..., title="Provide a clear summary of the focus area that you researched." + ) + findings: str = Field( + ..., + title="Give a clear and detailed overview of your findings based upon the expert interview.", + ) + thesis: str = Field( + ..., + title="Give a clear and specific investment thesis based upon these findings.", + ) + + class InterviewState(TypedDict): + messages: Annotated[List[AnyMessage], add_messages] + analyst: Analyst + section: Section + + class ResearchGraphState(TypedDict): + analysts: List[Analyst] + topic: str + max_analysts: int + sections: List[Section] + interviews: Annotated[list, operator.add] + + # Conditional edge + def route_messages(state): + return "ask_question" + + def generate_question(state): + return ... + + def generate_answer(state): + return ... + + # Add nodes and edges + interview_builder = StateGraph(InterviewState) + interview_builder.add_node("ask_question", generate_question) + interview_builder.add_node("answer_question", generate_answer) + + # Flow + interview_builder.add_edge(START, "ask_question") + interview_builder.add_edge("ask_question", "answer_question") + interview_builder.add_conditional_edges("answer_question", route_messages) + + # Set up memory + memory = MemorySaver() + + # Interview + interview_graph = interview_builder.compile(checkpointer=memory).with_config( + run_name="Conduct Interviews" + ) + + # View + assert interview_graph.get_graph().to_json() == snapshot + + def run_all_interviews(state: ResearchGraphState): + """Edge to run the interview sub-graph using Send""" + return [ + Send( + "conduct_interview", + { + "analyst": Analyst(), + "messages": [ + HumanMessage( + content="So you said you were writing an article on ...?" + ) + ], + }, + ) + for s in state["analysts"] + ] + + def generate_sections(state: ResearchGraphState): + return ... + + def generate_analysts(state: ResearchGraphState): + return ... + + builder = StateGraph(ResearchGraphState) + builder.add_node("generate_analysts", generate_analysts) + builder.add_node("conduct_interview", interview_builder.compile()) + builder.add_node("generate_sections", generate_sections) + + builder.add_edge(START, "generate_analysts") + builder.add_conditional_edges( + "generate_analysts", run_all_interviews, ["conduct_interview"] + ) + builder.add_edge("conduct_interview", "generate_sections") + builder.add_edge("generate_sections", END) + + graph = builder.compile() + + # View + assert graph.get_graph().to_json() == snapshot + assert graph.get_graph(xray=1).to_json() == snapshot