GenericFakeChatModel : implement the bind_tools method

[le-codeur-rapide]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

I am using this code :

tools = [Tool1, Tool2]
agent = create_tool_calling_agent(GenericFakeChatModel(messages), tools, prompt_template)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=False)

Description

Hello,
I want to test my agent and my tools without calling openai.
I see that there is already a GenericFakeChatModel implemented so I tried to use it, but the .bind_tools() method returns a not implemented error.

Is there already some kind of fake llm that can call tools implemented in langchain ?

The precise need would be a LLM that support the bind_tools method, can call tools (randomly or not) and return fake text as the final answer

Or is there an interest that I implement this myself ?

Thank you for your answer !

System Info

not relevant