SUTRA Streaming Mode
This guide explores SUTRA-V2’s streaming mode, enabling real-time, low-latency responses for dynamic applications like chatbots, live assistants, and interactive workflows. Streaming delivers responses incrementally, enhancing user experience with faster interactions.
🌐 Streaming Overview
SUTRA-V2’s streaming mode, supported via its OpenAI-compatible API, provides real-time response generation, ideal for applications requiring immediate feedback. Dedicated servers in India, the USA, Korea, and Japan (coming soon) optimize latency for global users.
📦 Step 1: Install Dependencies
# SUTRA models are OpenAI API compatible
!pip install -qU openai🔐 Step 2: Initialize SUTRA Client
from openai import OpenAI
client = OpenAI(
api_key="YOUR_SUTRA_API_KEY",
base_url="https://api.two.ai/v2"
)💬 Step 3: Streaming Chat Completion
stream = client.chat.completions.create(
model="sutra-v2",
messages=[{"role": "user", "content": "Write a short story in Hindi about an AI assistant."}],
max_tokens=1024,
temperature=0.7,
stream=True
)
for chunk in stream:
if len(chunk.choices) > 0 and chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end='', flush=True)🌟 Example: cURL for Streaming
curl -X POST "https://api.two.ai/v2/chat/completions" \
-H "Authorization: Bearer $SUTRA_API_KEY" \
-H "Content-Type: application/json" \
-H "Accept: text/event-stream" \
-d '{"model": "sutra-v2", "messages": [{"role": "user", "content": "मंगल ग्रह के बारे में बताएं"}], "stream": true}'🛠 Troubleshooting
- Stream Interruptions: Ensure a stable internet connection and verify the
stream=Trueparameter. - Invalid API Key: Check your key at https://developer.two.ai.
- Model Not Found: Use
sutra-v2. SUTRA-V1 was deprecated on March 22, 2025.