How can I deploy my flow as an API?

[nurettn]

How can I deploy my flow as an API so that I can use the chat with the flow using API endpoints? I think there's a feature like this but I couldn't see that in the documentation.

[dosubot[bot]]

To deploy your flow as an API and interact with it using API endpoints in Langflow, follow these steps:

1. Prepare a POST request to the /run/{flow_id} endpoint, replacing {flow_id} with the ID of the flow you wish to execute.

2. Include necessary headers in your request, such as Content-Type: application/json and x-api-key: YOUR_API_KEY for authentication.

3. Construct the request body with the input value and any tweaks. For example:

   {
     "inputs": {"text": "Sample input"},
     "tweaks": {}
   }

4. Send the request using a tool like curl, Postman, or a script. Here's a curl example:

   curl -X 'POST' \
     'http://<your_server>/api/v1/run/{flow_id}' \
     -H 'accept: application/json' \
     -H 'Content-Type: application/json' \
     -H 'x-api-key: YOUR_API_KEY' \
     -d '{
           "inputs": {"text": "Sample input"},
           "tweaks": {}
         }'

Or with Python using requests:

import requests

def run_flow(inputs: dict, flow_id: str, tweaks: dict = None, apiKey: str = None) -> dict:
    BASE_API_URL = "http://<your_server>/api/v1/run"
    api_url = f"{BASE_API_URL}/{flow_id}"
    payload = {"inputs": inputs}
    headers = {"Content-Type": "application/json"}

    if tweaks:
        payload["tweaks"] = tweaks
    if apiKey:
        headers["x-api-key"] = apiKey

    response = requests.post(api_url, json=payload, headers=headers)
    return response.json()

inputs = {"text": "Sample input"}
api_key = "YOUR_API_KEY"
flow_id = "your_flow_id"
print(run_flow(inputs, flow_id=flow_id, apiKey=api_key))

This will execute the specified flow with your input and return the results. Ensure to replace <your_server> with your actual server address and {flow_id} with the correct flow ID. For more details, refer to the source code and API documentation available in the Langflow GitHub repository.

Details

Sources

• src/backend/base/langflow/api/v1/endpoints.py
• docs/docs/administration/api.mdx
• src/backend/base/langflow/api/v1/flows.py
• src/backend/langflow/services/database/models/api_key/crud.py
• src/backend/base/langflow/schema/graph.py
• tests/test_endpoints.py
• scripts/gcp/deploy_langflow_gcp.sh
• scripts/gcp/deploy_langflow_gcp_spot.sh
• src/frontend/src/controllers/API/api.tsx

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.