Integrating vLLM with Fikra API

Prerequisites

• A Fikra API key (fk_live_...) generated from the Fikra dashboard.
• Python 3.8+ or Node.js 18+.
• The openai Python package or openai Node.js package installed.
• Access to the Fikra API base URL: https://api.fikraapi.co.ke/v1.

Environment Variable Setup

Set your Fikra API key as an environment variable to avoid hardcoding credentials:

export FIKRA_API_KEY="fk_live_your_key_here"

Python Example

Fikra API is OpenAI-compatible. You can use the standard openai Python SDK by pointing it to the Fikra base URL.

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

To enable streaming, set stream: true in the request. The API responds with Server-Sent Events (SSE).

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 JSON, missing required fields, or invalid model alias. Check the model registry for available aliases.
• 401 Unauthorized: Missing or invalid Authorization: Bearer fk_live_... header.
• 402 Payment Required: Insufficient token credits in your Fikra wallet. Top up via Paystack billing integration.
• 429 Too Many Requests: Rate limit exceeded. Unverified accounts are limited to 30 RPM; trusted accounts to 100 RPM.
• 503 Service Unavailable: Temporary server issue. Implement retry logic with exponential backoff.

Production Checklist

• [ ] Use environment variables for API keys; never hardcode them.
• [ ] Implement retry logic with exponential backoff for 429 and 503 errors.
• [ ] Monitor token usage via the Fikra dashboard to manage wallet balance.
• [ ] Validate model aliases against the current model registry before deployment.
• [ ] Test streaming behavior under load to ensure SSE handling is robust.
• [ ] Log request IDs for debugging and support purposes.