Integrating Fikra API with Langflow

Prerequisites

• A Fikra API account with a valid API key (fk_live_...).
• Langflow installed and running.
• Access to the Fikra dashboard to manage API keys and token credits.

Environment Variable Setup

Langflow supports OpenAI-compatible endpoints. To use Fikra API, configure the following environment variables in your Langflow environment or .env file:

FIKRA_API_KEY=fk_live_your_key_here
FIKRA_BASE_URL=https://api.fikraapi.co.ke/v1

In Langflow, when adding an LLM component, select the OpenAI provider type. Then, override the default base URL and API key with the Fikra-specific values above. This allows Langflow to route requests to Fikra’s OpenAI-compatible chat-completions interface.

Python Example

Below is a minimal Python example using the openai Python SDK, which is compatible with Fikra’s API. This pattern mirrors how Langflow internally communicates with OpenAI-compatible endpoints.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.fikraapi.co.ke/v1",
    api_key=os.getenv("FIKRA_API_KEY")
)

response = client.chat.completions.create(
    model="fikra-flash",
    messages=[
        {"role": "user", "content": "Hello, Fikra!"}
    ]
)

print(response.choices[0].message.content)

Streaming Guidance

Fikra supports streaming via Server-Sent Events (SSE) when stream: true is set. In Langflow, enable streaming in the LLM component settings if available. For direct SDK usage:

stream = client.chat.completions.create(
    model="fikra-flash",
    messages=[
        {"role": "user", "content": "Explain quantum computing simply."}
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Common Errors

• 400 Bad Request: Malformed request body or invalid model alias. Verify that model is one of the public Fikra aliases (e.g., fikra-flash).
• 401 Unauthorized: Missing or invalid Authorization: Bearer fk_live_... header. Check your FIKRA_API_KEY.
• 402 Payment Required: Insufficient token credits in your Fikra wallet. Top up via the Fikra dashboard.
• 429 Too Many Requests: Rate limit exceeded. Unverified accounts are limited to 30 RPM; trusted accounts to 100 RPM. Implement exponential backoff.
• 503 Service Unavailable: Temporary Fikra API outage. Retry with backoff and monitor the Fikra dashboard for status updates.

Production Checklist

• [ ] Store FIKRA_API_KEY in a secure environment variable or secrets manager.
• [ ] Use fikra-flash for low-latency tasks; check the model registry for other aliases.
• [ ] Implement retry logic with exponential backoff for 429 and 503 errors.
• [ ] Monitor token credit usage in the Fikra dashboard.
• [ ] Test streaming behavior in staging before production deployment.
• [ ] Validate that Langflow’s OpenAI-compatible configuration points to https://api.fikraapi.co.ke/v1.