-
Notifications
You must be signed in to change notification settings - Fork 4.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error 400 API mistralAI #5335
Comments
Hey @abelBEDOYA! I'm here to help you out with any bugs, questions, or contributions you might have. Let's get this issue sorted out together! The error you're encountering, "Tool call id has to be defined," suggests that the request to the MistralAI API is missing a required parameter or field related to the tool call ID. This is a common issue when the API expects a specific identifier for tool calls, which might not be automatically generated or included in your current setup. Here are a few steps you can take to troubleshoot and potentially resolve this issue:
If these steps do not resolve the issue, you may need to delve deeper into the Langflow codebase or consult additional resources to understand how tool call IDs are managed and passed to the MistralAI API. To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other |
I have just got this issue today, have you figured out what the issue is? Ive had a look and made sure both 'id' and 'tool_call_id' are not None and am still getting the same result |
Facing this issue since 18-Dec, I tried using Langgraph but the problem remains the same. Mistral api is expecting the tool_call_id but Langgraph doesn't seem to send that in the expected format after tool call. |
Bug Description
Hello,
I've been using langlfow to build a chatbot, a RAG and now an agent which can access a calculator tool.
Using OpenAI model with its key works fine. However when I try so with MistralAI it runs into this error:
The mistral model that is been used is misrtal-large-latest. If the model doesn't conclude that the tool has to be used, the chat doesn't run into this error. This happens with every model.
Reproduction
docker compose up
with this docker
Expected behavior
A new message which depends on the outcome of the calculator (calculator tool should have been used) with the correct result.
Who can help?
No response
Operating System
Ubuntu 22.04 (docker)
Langflow Version
1.1.1
Python Version
3.11
Screenshot
No response
Flow File
Simple Agent.json
The text was updated successfully, but these errors were encountered: