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

# gemini

> Google AI models

**Server path:** `/gemini` | **Type:** Application | **PCID required:** Yes

## Tools

| Tool                                                  | Description                                                 |
| ----------------------------------------------------- | ----------------------------------------------------------- |
| [`gemini_generate_content`](#gemini_generate_content) | Generate content using Google Gemini models                 |
| [`gemini_chat`](#gemini_chat)                         | Have a conversation using Gemini models                     |
| [`gemini_analyze_image`](#gemini_analyze_image)       | Analyze an image using Gemini vision capabilities           |
| [`gemini_embed_content`](#gemini_embed_content)       | Create embeddings for text using Gemini models              |
| [`gemini_list_models`](#gemini_list_models)           | List available Gemini models                                |
| [`gemini_count_tokens`](#gemini_count_tokens)         | Count tokens in text for Gemini models                      |
| [`gemini_generate_code`](#gemini_generate_code)       | Generate code using Gemini models optimized for programming |
| [`gemini_summarize_text`](#gemini_summarize_text)     | Summarize long text using Gemini models                     |

***

## gemini\_generate\_content

Generate content using Google Gemini models

**Parameters:**

| Parameter         | Type      | Required | Default              | Description                        |
| ----------------- | --------- | -------- | -------------------- | ---------------------------------- |
| `model`           | string    | No       | `"gemini-2.5-flash"` | Gemini model to use                |
| `prompt`          | string    | Yes      | —                    | Text prompt for content generation |
| `temperature`     | number    | No       | —                    | Sampling temperature               |
| `topP`            | number    | No       | —                    | Nucleus sampling parameter         |
| `topK`            | number    | No       | —                    | Top-k sampling parameter           |
| `maxOutputTokens` | number    | No       | —                    | Maximum tokens to generate         |
| `stopSequences`   | string\[] | No       | —                    | Stop sequences to end generation   |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "model": {
        "type": "string",
        "default": "gemini-2.5-flash",
        "description": "Gemini model to use"
      },
      "prompt": {
        "type": "string",
        "description": "Text prompt for content generation"
      },
      "temperature": {
        "type": "number",
        "description": "Sampling temperature"
      },
      "topP": {
        "type": "number",
        "description": "Nucleus sampling parameter"
      },
      "topK": {
        "type": "number",
        "description": "Top-k sampling parameter"
      },
      "maxOutputTokens": {
        "type": "number",
        "description": "Maximum tokens to generate"
      },
      "stopSequences": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Stop sequences to end generation"
      }
    },
    "required": [
      "PCID",
      "prompt"
    ]
  }
  ```
</Expandable>

***

## gemini\_chat

Have a conversation using Gemini models

**Parameters:**

| Parameter         | Type      | Required | Default              | Description                |
| ----------------- | --------- | -------- | -------------------- | -------------------------- |
| `model`           | string    | No       | `"gemini-2.5-flash"` | Gemini model to use        |
| `messages`        | object\[] | Yes      | —                    | Conversation history       |
| `temperature`     | number    | No       | —                    | Sampling temperature       |
| `maxOutputTokens` | number    | No       | —                    | Maximum tokens to generate |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "model": {
        "type": "string",
        "default": "gemini-2.5-flash",
        "description": "Gemini model to use"
      },
      "messages": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "role": {
              "type": "string",
              "enum": [
                "user",
                "model"
              ],
              "description": "Message role"
            },
            "parts": {
              "type": "array",
              "items": {
                "type": "object",
                "properties": {
                  "text": {
                    "type": "string",
                    "description": "Message text content"
                  }
                }
              },
              "description": "Message parts"
            }
          }
        },
        "description": "Conversation history"
      },
      "temperature": {
        "type": "number",
        "description": "Sampling temperature"
      },
      "maxOutputTokens": {
        "type": "number",
        "description": "Maximum tokens to generate"
      }
    },
    "required": [
      "PCID",
      "messages"
    ]
  }
  ```
</Expandable>

***

## gemini\_analyze\_image

Analyze an image using Gemini vision capabilities

**Parameters:**

| Parameter         | Type   | Required | Default              | Description                             |
| ----------------- | ------ | -------- | -------------------- | --------------------------------------- |
| `model`           | string | No       | `"gemini-2.5-flash"` | Gemini model with vision capabilities   |
| `imageUrl`        | string | No       | —                    | URL of image to analyze                 |
| `imageBase64`     | string | No       | —                    | Base64 encoded image data               |
| `prompt`          | string | Yes      | —                    | Question or instruction about the image |
| `temperature`     | number | No       | —                    | Sampling temperature                    |
| `maxOutputTokens` | number | No       | —                    | Maximum tokens to generate              |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "model": {
        "type": "string",
        "default": "gemini-2.5-flash",
        "description": "Gemini model with vision capabilities"
      },
      "imageUrl": {
        "type": "string",
        "description": "URL of image to analyze"
      },
      "imageBase64": {
        "type": "string",
        "description": "Base64 encoded image data"
      },
      "prompt": {
        "type": "string",
        "description": "Question or instruction about the image"
      },
      "temperature": {
        "type": "number",
        "description": "Sampling temperature"
      },
      "maxOutputTokens": {
        "type": "number",
        "description": "Maximum tokens to generate"
      }
    },
    "required": [
      "PCID",
      "prompt"
    ]
  }
  ```
</Expandable>

***

## gemini\_embed\_content

Create embeddings for text using Gemini models

**Parameters:**

| Parameter  | Type   | Required | Default                | Description                          |
| ---------- | ------ | -------- | ---------------------- | ------------------------------------ |
| `model`    | string | No       | `"text-embedding-004"` | Gemini embedding model               |
| `content`  | string | Yes      | —                      | Text content to embed                |
| `taskType` | string | No       | —                      | Task type for embedding optimization |
| `title`    | string | No       | —                      | Optional title for the content       |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "model": {
        "type": "string",
        "default": "text-embedding-004",
        "description": "Gemini embedding model"
      },
      "content": {
        "type": "string",
        "description": "Text content to embed"
      },
      "taskType": {
        "type": "string",
        "enum": [
          "RETRIEVAL_QUERY",
          "RETRIEVAL_DOCUMENT",
          "SEMANTIC_SIMILARITY",
          "CLASSIFICATION",
          "CLUSTERING"
        ],
        "description": "Task type for embedding optimization"
      },
      "title": {
        "type": "string",
        "description": "Optional title for the content"
      }
    },
    "required": [
      "PCID",
      "content"
    ]
  }
  ```
</Expandable>

***

## gemini\_list\_models

List available Gemini models

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      }
    },
    "required": [
      "PCID"
    ]
  }
  ```
</Expandable>

***

## gemini\_count\_tokens

Count tokens in text for Gemini models

**Parameters:**

| Parameter | Type   | Required | Default              | Description                     |
| --------- | ------ | -------- | -------------------- | ------------------------------- |
| `model`   | string | No       | `"gemini-2.5-flash"` | Gemini model for token counting |
| `text`    | string | Yes      | —                    | Text to count tokens for        |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "model": {
        "type": "string",
        "default": "gemini-2.5-flash",
        "description": "Gemini model for token counting"
      },
      "text": {
        "type": "string",
        "description": "Text to count tokens for"
      }
    },
    "required": [
      "PCID",
      "text"
    ]
  }
  ```
</Expandable>

***

## gemini\_generate\_code

Generate code using Gemini models optimized for programming

**Parameters:**

| Parameter         | Type   | Required | Default              | Description                                         |
| ----------------- | ------ | -------- | -------------------- | --------------------------------------------------- |
| `model`           | string | No       | `"gemini-2.5-flash"` | Gemini model to use                                 |
| `prompt`          | string | Yes      | —                    | Code generation prompt                              |
| `language`        | string | No       | —                    | Programming language (e.g., "python", "javascript") |
| `temperature`     | number | No       | —                    | Low temperature for more deterministic code         |
| `maxOutputTokens` | number | No       | —                    | Maximum tokens to generate                          |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "model": {
        "type": "string",
        "default": "gemini-2.5-flash",
        "description": "Gemini model to use"
      },
      "prompt": {
        "type": "string",
        "description": "Code generation prompt"
      },
      "language": {
        "type": "string",
        "description": "Programming language (e.g., \"python\", \"javascript\")"
      },
      "temperature": {
        "type": "number",
        "default": 0.1,
        "description": "Low temperature for more deterministic code"
      },
      "maxOutputTokens": {
        "type": "number",
        "description": "Maximum tokens to generate"
      }
    },
    "required": [
      "PCID",
      "prompt"
    ]
  }
  ```
</Expandable>

***

## gemini\_summarize\_text

Summarize long text using Gemini models

**Parameters:**

| Parameter       | Type      | Required | Default              | Description                           |
| --------------- | --------- | -------- | -------------------- | ------------------------------------- |
| `model`         | string    | No       | `"gemini-2.5-flash"` | Gemini model to use                   |
| `text`          | string    | Yes      | —                    | Text to summarize                     |
| `summaryLength` | string    | No       | `"medium"`           | Desired summary length                |
| `focusAreas`    | string\[] | No       | —                    | Specific areas to focus on in summary |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID"
      },
      "model": {
        "type": "string",
        "default": "gemini-2.5-flash",
        "description": "Gemini model to use"
      },
      "text": {
        "type": "string",
        "description": "Text to summarize"
      },
      "summaryLength": {
        "type": "string",
        "enum": [
          "short",
          "medium",
          "long"
        ],
        "default": "medium",
        "description": "Desired summary length"
      },
      "focusAreas": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Specific areas to focus on in summary"
      }
    },
    "required": [
      "PCID",
      "text"
    ]
  }
  ```
</Expandable>