Skip to content

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

3.6 KB
Raw Blame
---
title: Groq
description: "AgentOps provides first class support for Groq"
---

import CodeTooltip from '/snippets/add-code-tooltip.mdx'
import EnvTooltip from '/snippets/add-env-tooltip.mdx'

[Groq](https://groq.com) accelerates LLM inference with its ultra-fast Language Processing Unit (LPU) that powers Groq Cloud. Explore the [Groq docs](https://console.groq.com/docs/overview) to get started with their developer console.

## Steps to Integrate Groq with AgentOps

<Steps>
  <Step title="Install the AgentOps SDK">
    <CodeGroup>
      ```bash pip 
      pip install agentops
      ```
      ```bash poetry
      poetry add agentops
      ```
    </CodeGroup>
  </Step>
  <Step title="Install the Groq SDK">
    <CodeGroup>
      ```bash pip
      pip install groq
      ```
      ```bash poetry
      poetry add groq
      ```
    </CodeGroup>
  </Step>
  <Step title="Initialize AgentOps and develop with Groq">
    <CodeTooltip/>
    <CodeGroup>
      ```python python
      from groq import Groq
      import agentops

      agentops.init(<INSERT YOUR API KEY HERE>)
      client = Groq(api_key="your_api_key")
      
      # Your code here...

      agentops.end_session('Success')
      ```
    </CodeGroup>
    <EnvTooltip />
      <CodeGroup>
        ```python .env
        AGENTOPS_API_KEY=<YOUR API KEY>
        GROQ_API_KEY=<YOUR OPENAI API KEY>
        ```
      </CodeGroup>
      Read more about environment variables in [Advanced Configuration](/v1/usage/advanced-configuration)
  </Step>
  <Step title="Run your Agent">
    Execute your program and visit [app.agentops.ai/drilldown](https://app.agentops.ai/drilldown) to observe your Agent! 🕵️
    <Tip>
      After your run, AgentOps prints a clickable url to console linking directly to your session in the Dashboard
    </Tip>
    <div/>
    <Frame type="glass" caption="Clickable link to session">
      <img height="200" src="https://github.com/AgentOps-AI/agentops/blob/main/docs/images/external/groq/groq_session.png?raw=true" />
    </Frame>
  </Step>
</Steps>

## Full Examples

<CodeGroup>

```python sync
from groq import Groq
import agentops

agentops.init(<INSERT YOUR API KEY HERE>)
client = Groq(api_key="your_api_key")

response = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "Explain the importance of low latency LLMs",
        }
    ],
    model="llama3-8b-8192",
)

print(response.choices[0].message.content)
agentops.end_session('Success')
```

```python async
from groq import AsyncGroq
import agentops
import asyncio

async def main() -> None:
    agentops.init(<INSERT YOUR API KEY HERE>)
    client = AsyncGroq(api_key="your_api_key")

    response = await client.chat.completions.create(
        messages=[
            {
                "role": "user",
                "content": "Explain the importance of low latency LLMs",
            }
        ],
        model="llama3-8b-8192",
    )

    print(response.choices[0].message.content)
    agentops.end_session('Success')

asyncio.run(main())
```

</CodeGroup>

<Card title="Multi Agent Example" icon="bolt" href="https://github.com/AgentOps-AI/agentops/blob/main/examples/multi_agent_groq_example.ipynb">
    This notebook demonstrates how to use AgentOps with a multi-agent system using Groq.
</Card>

<script type="module" src="/scripts/github_stars.js"></script>
<script type="module" src="/scripts/scroll-img-fadein-animation.js"></script>
<script type="module" src="/scripts/button_heartbeat_animation.js"></script>
<script type="css" src="/styles/styles.css"></script>
<script type="module" src="/scripts/adjust_api_dynamically.js"></script>