Skip to main content

Data Source

Follow the instructions below to create a new data flow that ingests data from a Mistral AI source in Nexla.
mistral_llm_api.png

Mistral AI

Create a New Data Flow​

  1. To create a new data flow, navigate to the Integrate section, and click the New Data Flow button. Then, select the desired flow type from the list, and click the Create button.

  2. Select the Mistral AI connector tile from the list of available connectors. Then, select the credential that will be used to connect to your Mistral AI account, and click Next; or, create a new Mistral AI credential for use in this flow.

  3. In Nexla, Mistral AI data sources can be created using pre-built endpoint templates, which expedite source setup for common Mistral AI endpoints. Each template is designed specifically for the corresponding Mistral AI endpoint, making source configuration easy and efficient.
    • To configure this source using a template, follow the instructions in Configure Using a Template.

    Mistral AI sources can also be configured manually, allowing you to interact with Mistral AI endpoints not included in the pre-built templates or apply further customizations to exactly suit your needs.
    • To configure this source manually, follow the instructions in Configure Manually.

Configure Using a Template​

Nexla provides pre-built templates that can be used to rapidly configure data sources to interact with common Mistral AI endpoints. Each template is designed specifically for the corresponding Mistral AI endpoint, making data source setup easy and efficient.

Endpoint Settings​

  • Select the endpoint from which this source will fetch data from the Endpoint pulldown menu. Available endpoint templates are listed in the expandable boxes below. Click on an endpoint to see more information about it and how to configure your data source for this endpoint.

    Chat Completion

    This endpoint template sends a chat completion request to the Mistral AI API and retrieves the AI-generated response. Use this template when you need to interact with Mistral AI's language models to generate text, answer questions, or perform natural language processing tasks.

    • Enter your message or prompt in the Message field. This should be the text you want to send to the Mistral AI model for processing. The message is sent as part of a chat completion request with the role set to "user" and the content set to your message. The Mistral AI model will process this message and generate an appropriate response.

    This endpoint sends a POST request to the Mistral AI chat completion endpoint with your message in the request body. The request body format is {"messages":[{"role":"user","content":"{your_message}"}]}. The endpoint returns the AI-generated response from the Mistral AI model configured in your credential.

    The model used for processing is determined by the Model Name configured in your credential. Different models may have different capabilities, response times, and costs. For detailed information about available models, chat completion formats, API endpoints, and response structures, see the Mistral AI API documentation.

Endpoint Testing​

Once the selected endpoint template has been configured, Nexla can retrieve a sample of the data that will be fetched according to the current settings. This allows users to verify that the source is configured correctly before saving.

  • To test the current endpoint configuration, click the Test button to the right of the endpoint selection menu. Sample data will be fetched & displayed in the Endpoint Test Result panel on the right.

  • If the sample data is not as expected, review the selected endpoint and associated settings, and make any necessary adjustments. Then, click the Test button again, and check the sample data to ensure that the correct information is displayed.

Configure Manually​

Mistral AI data sources can be manually configured to interact with any valid Mistral AI API endpoint. Manual configuration provides maximum flexibility for accessing endpoints not covered by pre-built templates or when you need custom API configurations.

With manual configuration, you can also create more complex Mistral AI sources, such as sources that use multiple API calls or sources that require custom request parameters or headers.

API Method​

  1. To manually configure this source, select the Advanced tab at the top of the configuration screen.

  2. Select the API method that will be used for calls to the Mistral AI API from the Method pulldown menu. Mistral AI API typically uses POST method for chat completion and other LLM operations.

API Endpoint URL​

  1. Enter the URL of the Mistral AI API endpoint from which this source will fetch data in the Set API URL field. This should be the complete URL to your Mistral AI endpoint, typically the base URL configured in your credential (e.g., https://api.mistral.ai/v1/chat/completions).

Ensure the API endpoint URL is correct and accessible with your current credentials. The Mistral AI API endpoint URL should point to the specific endpoint you want to use (e.g., chat completions, embeddings). You can test the endpoint using the Test button after configuring the URL.

Request Body​

  1. Configure the request body that will be sent to the Mistral AI API. The request body should contain your request parameters formatted as JSON. For chat completion requests, the request body format is typically {"messages":[{"role":"user","content":"{your_message}"}]}. You can customize the request body to include additional parameters like temperature, max_tokens, or system prompts.

The request body must be valid JSON and must match the Mistral AI API's expected format for the specific endpoint you're using. For chat completion endpoints, the request body should include a messages array with message objects containing role and content properties. For detailed information about request body formats, available parameters, and API endpoints, see the Mistral AI API documentation.

Response Data Path​

  1. Enter the JSONPath expression in the Response Data Path field to specify which part of the API response should be treated as the relevant data by Nexla. For Mistral AI API responses, use $ to extract the entire response object, or $.choices[*] to extract all choices from a chat completion response.

The JSONPath expression must correctly reference the structure of your Mistral AI API response. Mistral AI API responses may return data in different structures depending on the endpoint. Ensure your JSONPath expression matches the structure returned by your specific endpoint. The JSONPath expression determines which data will be extracted and processed by Nexla.

Save the Data Source​

  1. Once all of the relevant steps in the above sections have been completed, click the Next button to proceed with the rest of the data flow configuration, or click Save to save the data source configuration for later use.