Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-10 01:10:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: fmt concepts (#24999)

Browse Source
This commit is contained in:
Bagatur 2024-08-02 13:35:45 -07:00 committed by GitHub
parent dd8e4cd020
commit 64ccddf3cb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 22 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
docs/docs/concepts.mdx
View File

@ -542,7 +542,8 @@ Typical usage may look like the following:
```python ```python
tools = [...] # Define a list of tools tools = [...] # Define a list of tools
llm_with_tools = llm.bind_tools(tools) llm_with_tools = llm.bind_tools(tools)
ai_msg = llm_with_tools.invoke("do xyz...") # AIMessage(tool_calls=[ToolCall(...), ...], ...) ai_msg = llm_with_tools.invoke("do xyz...")
# -> AIMessage(tool_calls=[ToolCall(...), ...], ...)
``` ```
The `AIMessage` returned from the model MAY have `tool_calls` associated with it. The `AIMessage` returned from the model MAY have `tool_calls` associated with it.
@ -559,9 +560,14 @@ This generally looks like:
```python ```python
# You will want to previously check that the LLM returned tool calls # You will want to previously check that the LLM returned tool calls
tool_call = ai_msg.tool_calls[0] # ToolCall(args={...}, id=..., ...) tool_call = ai_msg.tool_calls[0]
# ToolCall(args={...}, id=..., ...)
tool_output = tool.invoke(tool_call["args"]) tool_output = tool.invoke(tool_call["args"])
tool_message = ToolMessage(content=tool_output, tool_call_id=tool_call["id"], name=tool_call["name"]) tool_message = ToolMessage(
content=tool_output,
tool_call_id=tool_call["id"],
name=tool_call["name"]
)
``` ```
Note that the `content` field will generally be passed back to the model. Note that the `content` field will generally be passed back to the model.
@ -571,7 +577,12 @@ you can transform the tool output but also pass it as an artifact (read more abo
```python ```python
... # Same code as above ... # Same code as above
response_for_llm = transform(response) response_for_llm = transform(response)
tool_message = ToolMessage(content=response_for_llm, tool_call_id=tool_call["id"], name=tool_call["name"], artifact=tool_output) tool_message = ToolMessage(
content=response_for_llm,
tool_call_id=tool_call["id"],
name=tool_call["name"],
artifact=tool_output
)
``` ```
#### Invoke with `ToolCall` #### Invoke with `ToolCall`
@ -582,9 +593,14 @@ The benefits of this are that you don't have to write the logic yourself to tran
This generally looks like: This generally looks like:
```python ```python
tool_call = ai_msg.tool_calls[0] # ToolCall(args={...}, id=..., ...) tool_call = ai_msg.tool_calls[0]
# -> ToolCall(args={...}, id=..., ...)
tool_message = tool.invoke(tool_call) tool_message = tool.invoke(tool_call)
# -> ToolMessage(content="tool result foobar...", tool_call_id=..., name="tool_name") # -> ToolMessage(
content="tool result foobar...",
tool_call_id=...,
name="tool_name"
)
``` ```
If you are invoking the tool this way and want to include an [artifact](/docs/concepts/#toolmessage) for the ToolMessage, you will need to have the tool return two things. If you are invoking the tool this way and want to include an [artifact](/docs/concepts/#toolmessage) for the ToolMessage, you will need to have the tool return two things.