Packages

req_llm

1.2.0
1.28.0 1.27.0 1.26.0 1.25.0 1.24.0 1.23.0 1.22.0 1.21.1 1.21.0 1.20.0 1.19.0 1.18.0 1.17.1 1.17.0 1.16.0 1.15.0 1.14.0 1.13.0 1.12.0 1.11.0 1.10.0 1.9.0 1.8.0 1.7.1 1.7.0 1.6.0 1.5.1 1.5.0 1.4.1 1.4.0 1.3.0 1.2.0 1.1.0 1.0.0 1.0.0-rc.8 1.0.0-rc.7 1.0.0-rc.6 1.0.0-rc.5 1.0.0-rc.4 1.0.0-rc.3 1.0.0-rc.2 1.0.0-rc.1

Composable Elixir library for LLM interactions built on Req & Finch

HexDocs Report package

Current section

Files

Jump to
Documentation
Changelog
License
42 Versions
12 Dependencies
Dependants
Files
Activity
req_llm guides google.md
Raw

guides/google.md 

# Google (Gemini)

Access Gemini models with built-in web grounding and thinking capabilities.

## Configuration

```bash
GOOGLE_API_KEY=AIza...
```

## Provider Options

Passed via `:provider_options` keyword:

### `google_api_version`
- **Type**: `"v1"` | `"v1beta"`
- **Default**: `"v1"`
- **Purpose**: Select API version (v1beta required for grounding)
- **Example**: `provider_options: [google_api_version: "v1beta"]`
- **Note**: Auto-set to v1beta when `google_grounding` is used

### `google_grounding`
- **Type**: Map
- **Purpose**: Enable Google Search grounding (requires v1beta)
- **Modern (Gemini 2.5)**: `%{enable: true}`
- **Legacy (Gemini 1.5)**: `%{dynamic_retrieval: %{mode: "MODE_DYNAMIC", dynamic_threshold: 0.7}}`
- **Example**: `provider_options: [google_grounding: %{enable: true}]`

### `google_thinking_budget`
- **Type**: Non-negative integer
- **Purpose**: Control thinking tokens for Gemini 2.5 models
- **`0`**: Disable thinking
- **Omit**: Dynamic allocation (default)
- **Example**: `provider_options: [google_thinking_budget: 4096]`

### `google_safety_settings`
- **Type**: List of maps
- **Purpose**: Configure content safety filters
- **Categories**: `HARM_CATEGORY_HATE_SPEECH`, `HARM_CATEGORY_DANGEROUS_CONTENT`, `HARM_CATEGORY_HARASSMENT`, `HARM_CATEGORY_SEXUALLY_EXPLICIT`
- **Thresholds**: `BLOCK_NONE`, `BLOCK_ONLY_HIGH`, `BLOCK_MEDIUM_AND_ABOVE`, `BLOCK_LOW_AND_ABOVE`
- **Example**:
  ```elixir
  provider_options: [
    google_safety_settings: [
      %{category: "HARM_CATEGORY_HATE_SPEECH", threshold: "BLOCK_MEDIUM_AND_ABOVE"}
    ]
  ]
  ```

### `google_candidate_count`
- **Type**: Positive integer
- **Default**: `1`
- **Purpose**: Generate multiple candidates (only first returned)
- **Example**: `provider_options: [google_candidate_count: 3]`

### Embedding Options

#### `dimensions`
- **Type**: `128..3072`
- **Purpose**: Control embedding vector dimensions
- **Recommended**: `768`, `1536`, or `3072`
- **Example**: `provider_options: [dimensions: 768]`

#### `task_type`
- **Type**: String
- **Purpose**: Specify embedding task type
- **Values**: `RETRIEVAL_QUERY`, `RETRIEVAL_DOCUMENT`, `SEMANTIC_SIMILARITY`, `CLASSIFICATION`
- **Example**: `provider_options: [task_type: "RETRIEVAL_QUERY"]`

#### `title`
- **Type**: String
- **Purpose**: Document title for better embedding quality
- **Example**: `provider_options: [title: "Product Documentation", task_type: "RETRIEVAL_DOCUMENT"]`

## Wire Format Notes

- Endpoint: `/models/{model}:generateContent`
- Auth: API key in query param or header
- System: Separate `systemInstruction` field
- Safety: Gemini-specific safety configuration

All differences handled automatically by ReqLLM.

## Resources

- [Google AI Documentation](https://ai.google.dev/docs)
- [Gemini API Reference](https://ai.google.dev/api/rest)