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

3.4 KB
Raw Blame
---
title: Gemini
description: "Explore Google DeepMind's Gemini with observation via AgentOps"
---

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

[Gemini (Google Generative AI)](https://ai.google.dev/gemini-api/docs/quickstart) is a leading provider of AI tools and services.
Explore the [Gemini API](https://ai.google.dev/docs) for more information.

<Note>
  `google-generativeai>=0.1.0` is currently supported.
</Note>

<Steps>
  <Step title="Install the AgentOps SDK">
    <CodeGroup>
      ```bash pip 
      pip install agentops
      ```
      ```bash poetry
      poetry add agentops
      ```
    </CodeGroup>
  </Step>
  <Step title="Install the Gemini SDK">
    <Note>
      `google-generativeai>=0.1.0` is required for Gemini integration.
    </Note>
    <CodeGroup>
      ```bash pip
      pip install google-generativeai
      ```
      ```bash poetry
      poetry add google-generativeai
      ```
    </CodeGroup>
  </Step>
  <Step title="Add 3 lines of code">
    <CodeTooltip/>
    <CodeGroup>
      ```python python
      import google.generativeai as genai
      import agentops
      
      agentops.init(<INSERT YOUR API KEY HERE>)
      model = genai.GenerativeModel("gemini-1.5-flash")
      ...
      # End of program (e.g. main.py)
      agentops.end_session("Success") # Success|Fail|Indeterminate
      ```
    </CodeGroup>
    <EnvTooltip />
      <CodeGroup>
        ```python .env
        AGENTOPS_API_KEY=<YOUR API KEY>
        GEMINI_API_KEY=<YOUR GEMINI 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/link-to-session.gif?raw=true" />
    </Frame>
  </Step>
</Steps>

## Full Examples

<CodeGroup>
  ```python sync
  import google.generativeai as genai
  import agentops

  agentops.init(<INSERT YOUR API KEY HERE>)
  model = genai.GenerativeModel("gemini-1.5-flash")

  response = model.generate_content(
      "Write a haiku about AI and humans working together"
  )

  print(response.text)
  agentops.end_session('Success')
  ```

  ```python stream
  import google.generativeai as genai
  import agentops

  agentops.init(<INSERT YOUR API KEY HERE>)
  model = genai.GenerativeModel("gemini-1.5-flash")

  response = model.generate_content(
      "Write a haiku about AI and humans working together",
      stream=True
  )

  for chunk in response:
      print(chunk.text, end="")

  agentops.end_session('Success')
  ```
</CodeGroup>

You can find more examples in the [Gemini Examples](/v1/examples/gemini_examples) section.

<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>