> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langtrace.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini

> Gemini is an AI-driven platform that enhances conversational experiences by enabling seamless user-system interactions. Integrated with Langtrace, it provides deep language tracing and insights into dialogue patterns. This combination helps optimize AI-driven conversations for improved efficiency and user satisfaction.

Using Langtrace to monitor your Gemini backed LLM apps is quick and easy. Follow these steps:

## Setup

1. Install Langtrace's SDK and [initialize](/quickstart) the SDK in your code.

*Note: You'll need API keys from Langtrace and Gemini. Sign up for [Langtrace](https://langtrace.ai) and/or [Gemini](https://aistudio.google.com/app/apikey) if you haven't done so already.*

```bash Python theme={null}
# Install the SDK
pip install -U langtrace-python-sdk
```

```bash Shell theme={null}
pip install -q -U google-generativeai
```

2. Setup environment variables:

```bash Shell theme={null}
export LANGTRACE_API_KEY=YOUR_LANGTRACE_API_KEY
export GEMINI_API_KEY=YOUR_GEMINI_API_KEY
```

## Usage

Generate a simple output with your deployment's model:

<CodeGroup>
  ```python Python theme={null}
  import google.generativeai as genai
  import os
  from langtrace_python_sdk import langtrace, with_langtrace_root_span  # Must precede any llm module imports

  langtrace.init(api_key=os.environ["LANGTRACE_API_KEY"])


  @with_langtrace_root_span("chat_complete")
  def chat_complete():
      model = genai.GenerativeModel("gemini-1.5-flash")
      genai.configure(api_key=os.environ["GEMINI_API_KEY"])

      chat_response = genai.chat.complete(
          model=model,
          response=model.generate_content("Write a story about a magic backpack.")

      )
      print(chat_response.text)
      print(chat_response.choices[0].response.content)

  chat_complete()

  ```
</CodeGroup>