The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
docs[patch]: In conceptual docs explain constraints on ToolMessage (#26792)
Eugene Yurtsev27c12146c830
diff --git a/docs/docs/concepts.mdx b/docs/docs/concepts.mdxindex 0e5fdc500b..1efb3e25da 100644--- a/docs/docs/concepts.mdx+++ b/docs/docs/concepts.mdx@@ -116,14 +116,14 @@ These also have corresponding async methods that should be used with [asyncio](hThe **input type** and **output type** varies by component:-| Component | Input Type | Output Type |-| --- | --- | --- |-| Prompt | Dictionary | PromptValue |-| ChatModel | Single string, list of chat messages or a PromptValue | ChatMessage |-| LLM | Single string, list of chat messages or a PromptValue | String |-| OutputParser | The output of an LLM or ChatModel | Depends on the parser |-| Retriever | Single string | List of Documents |-| Tool | Single string or dictionary, depending on the tool | Depends on the tool |+| Component | Input Type | Output Type |+|--------------|-------------------------------------------------------|-----------------------|+| Prompt | Dictionary | PromptValue |+| ChatModel | Single string, list of chat messages or a PromptValue | ChatMessage |+| LLM | Single string, list of chat messages or a PromptValue | String |+| OutputParser | The output of an LLM or ChatModel | Depends on the parser |+| Retriever | Single string | List of Documents |+| Tool | Single string or dictionary, depending on the tool | Depends on the tool |All runnables expose input and output **schemas** to inspect the inputs and outputs:@@ -236,7 +236,7 @@ This is where information like log-probs and token usage may be stored.**`tool_calls`**-These represent a decision from an language model to call a tool. They are included as part of an `AIMessage` output.+These represent a decision from a language model to call a tool. They are included as part of an `AIMessage` output.They can be accessed from there with the `.tool_calls` property.This property returns a list of `ToolCall`s. A `ToolCall` is a dictionary with the following arguments:@@ -256,6 +256,8 @@ This represents a message with role "tool", which contains the result of calling- a `tool_call_id` field which conveys the id of the call to the tool that was called to produce this result.- an `artifact` field which can be used to pass along arbitrary artifacts of the tool execution which are useful to track but which should not be sent to the model.+With most chat models, a `ToolMessage` can only appear in the chat history after an `AIMessage` that has a populated `tool_calls` field.+#### (Legacy) FunctionMessageThis is a legacy message type, corresponding to OpenAI's legacy function-calling API. `ToolMessage` should be used instead to correspond to the updated tool-calling API.