Replicate

1
{
2
  "mcpServers": {
3
    "respan-docs": {
4
      "url": "https://docs.respan.ai/mcp"
5
    }
6
  }
7
}

What is Replicate?

Replicate is a platform for running machine learning models in the cloud. It hosts thousands of open-source models and provides a simple API for running predictions without managing infrastructure.

Setup

$
pip install respan-ai opentelemetry-instrumentation-replicate replicate python-dotenv

$
export REPLICATE_API_TOKEN="YOUR_REPLICATE_API_TOKEN"
$
export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$
export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.respan.ai/api"
$
export OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer $RESPAN_API_KEY"

1
import os
2
from dotenv import load_dotenv
3
4
load_dotenv()
5
6
import replicate
7
from respan import Respan
8
9
# Auto-discover and activate all installed instrumentors
10
respan = Respan(is_auto_instrument=True)
11
12
# Run a prediction — auto-traced by Respan
13
output = replicate.run(
14
    "meta/llama-2-70b-chat",
15
    input={"prompt": "Say hello in three languages."},
16
)
17
print("".join(output))
18
respan.flush()

What gets traced

• Model name and version
• Input parameters
• Prediction output
• Latency and processing time
• Token usage (for language models)

Traces appear in the Traces dashboard.

Learn more

• OpenTelemetry integration - How Respan processes OTel spans
• Respan Python SDK - Full SDK reference