> ## 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.

# ollama

> Ollama LLM API

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

## Tools

| Tool                                  | Description             |
| ------------------------------------- | ----------------------- |
| [`ollama_chat`](#ollama_chat)         | Generate a chat message |
| [`ollama_copy`](#ollama_copy)         | Copy a model            |
| [`ollama_create`](#ollama_create)     | Create a model          |
| [`ollama_delete`](#ollama_delete)     | Delete a model          |
| [`ollama_embed`](#ollama_embed)       | Generate embeddings     |
| [`ollama_generate`](#ollama_generate) | Generate a response     |
| [`ollama_list`](#ollama_list)         | List models             |
| [`ollama_ps`](#ollama_ps)             | List running models     |
| [`ollama_pull`](#ollama_pull)         | Pull a model            |
| [`ollama_push`](#ollama_push)         | Push a model            |
| [`ollama_show`](#ollama_show)         | Show model details      |
| [`ollama_version`](#ollama_version)   | Get version             |

***

## ollama\_chat

Generate a chat message

**Parameters:**

| Parameter      | Type      | Required | Default | Description                                                                                                                                                                                                            |
| -------------- | --------- | -------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `format`       | object    | No       | —       | Format to return a response in. Can be `json` or a JSON schema                                                                                                                                                         |
| `keep_alive`   | object    | No       | —       | Model keep-alive duration (for example `5m` or `0` to unload immediately)                                                                                                                                              |
| `logprobs`     | boolean   | No       | —       | Whether to return log probabilities of the output tokens                                                                                                                                                               |
| `messages`     | object\[] | Yes      | —       | Chat history as an array of message objects (each with a role and content)                                                                                                                                             |
| `model`        | string    | Yes      | —       | Model name                                                                                                                                                                                                             |
| `options`      | object    | No       | —       | Runtime options that control text generation                                                                                                                                                                           |
| `stream`       | boolean   | No       | —       | The stream value                                                                                                                                                                                                       |
| `think`        | object    | No       | —       | When true, returns separate thinking output in addition to content. Can be a boolean (true/false) or a string ("high", "medium", "low", "max") for supported models, with "max" requesting the highest thinking level. |
| `tools`        | object\[] | No       | —       | Optional list of function tools the model may call during the chat                                                                                                                                                     |
| `top_logprobs` | integer   | No       | —       | Number of most likely tokens to return at each token position when logprobs are enabled                                                                                                                                |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "format": {
        "description": "Format to return a response in. Can be `json` or a JSON schema"
      },
      "keep_alive": {
        "description": "Model keep-alive duration (for example `5m` or `0` to unload immediately)"
      },
      "logprobs": {
        "type": "boolean",
        "description": "Whether to return log probabilities of the output tokens"
      },
      "messages": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "role": {
              "type": "string",
              "enum": [
                "system",
                "user",
                "assistant",
                "tool"
              ],
              "description": "Author of the message."
            },
            "content": {
              "type": "string",
              "description": "Message text content"
            },
            "images": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Optional list of inline images for multimodal models"
            },
            "tool_calls": {
              "type": "array",
              "items": {
                "type": "object",
                "properties": {
                  "function": {
                    "type": "object"
                  }
                }
              },
              "description": "Tool call requests produced by the model"
            }
          },
          "required": [
            "role",
            "content"
          ]
        },
        "description": "Chat history as an array of message objects (each with a role and content)"
      },
      "model": {
        "type": "string",
        "description": "Model name"
      },
      "options": {
        "type": "object",
        "description": "Runtime options that control text generation",
        "properties": {
          "seed": {
            "type": "integer",
            "description": "Random seed used for reproducible outputs"
          },
          "temperature": {
            "type": "number",
            "description": "Controls randomness in generation (higher = more random)"
          },
          "top_k": {
            "type": "integer",
            "description": "Limits next token selection to the K most likely"
          },
          "top_p": {
            "type": "number",
            "description": "Cumulative probability threshold for nucleus sampling"
          },
          "min_p": {
            "type": "number",
            "description": "Minimum probability threshold for token selection"
          },
          "stop": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Stop sequences that will halt generation"
          },
          "num_ctx": {
            "type": "integer",
            "description": "Context length size (number of tokens)"
          },
          "num_predict": {
            "type": "integer",
            "description": "Maximum number of tokens to generate"
          }
        }
      },
      "stream": {
        "type": "boolean",
        "description": "The stream value"
      },
      "think": {
        "description": "When true, returns separate thinking output in addition to content. Can be a boolean (true/false) or a string (\"high\", \"medium\", \"low\", \"max\") for supported models, with \"max\" requesting the highest thinking level."
      },
      "tools": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "type": {
              "type": "string",
              "enum": [
                "function"
              ],
              "description": "Type of tool (always `function`)"
            },
            "function": {
              "type": "object",
              "description": "The function value"
            }
          },
          "required": [
            "type",
            "function"
          ]
        },
        "description": "Optional list of function tools the model may call during the chat"
      },
      "top_logprobs": {
        "type": "integer",
        "description": "Number of most likely tokens to return at each token position when logprobs are enabled"
      }
    },
    "required": [
      "PCID",
      "messages",
      "model"
    ]
  }
  ```
</Expandable>

***

## ollama\_copy

Copy a model

**Parameters:**

| Parameter     | Type   | Required | Default | Description                      |
| ------------- | ------ | -------- | ------- | -------------------------------- |
| `destination` | string | Yes      | —       | New model name to create         |
| `source`      | string | Yes      | —       | Existing model name to copy from |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "destination": {
        "type": "string",
        "description": "New model name to create"
      },
      "source": {
        "type": "string",
        "description": "Existing model name to copy from"
      }
    },
    "required": [
      "PCID",
      "destination",
      "source"
    ]
  }
  ```
</Expandable>

***

## ollama\_create

Create a model

**Parameters:**

| Parameter    | Type      | Required | Default | Description                                         |
| ------------ | --------- | -------- | ------- | --------------------------------------------------- |
| `from`       | string    | No       | —       | Existing model to create from                       |
| `license`    | string\[] | No       | —       | License string or list of licenses for the model    |
| `messages`   | object\[] | No       | —       | Message history to use for the model                |
| `model`      | string    | Yes      | —       | Name for the model to create                        |
| `parameters` | object    | No       | —       | Key-value parameters for the model                  |
| `quantize`   | string    | No       | —       | Quantization level to apply (e.g. `q4_K_M`, `q8_0`) |
| `stream`     | boolean   | No       | —       | Stream status updates                               |
| `system`     | string    | No       | —       | System prompt to embed in the model                 |
| `template`   | string    | No       | —       | Prompt template to use for the model                |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "from": {
        "type": "string",
        "description": "Existing model to create from"
      },
      "license": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "License string or list of licenses for the model"
      },
      "messages": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "role": {
              "type": "string",
              "enum": [
                "system",
                "user",
                "assistant",
                "tool"
              ],
              "description": "Author of the message."
            },
            "content": {
              "type": "string",
              "description": "Message text content"
            },
            "images": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Optional list of inline images for multimodal models"
            },
            "tool_calls": {
              "type": "array",
              "items": {
                "type": "object",
                "properties": {
                  "function": {
                    "type": "object"
                  }
                }
              },
              "description": "Tool call requests produced by the model"
            }
          },
          "required": [
            "role",
            "content"
          ]
        },
        "description": "Message history to use for the model"
      },
      "model": {
        "type": "string",
        "description": "Name for the model to create"
      },
      "parameters": {
        "type": "object",
        "description": "Key-value parameters for the model"
      },
      "quantize": {
        "type": "string",
        "description": "Quantization level to apply (e.g. `q4_K_M`, `q8_0`)"
      },
      "stream": {
        "type": "boolean",
        "description": "Stream status updates"
      },
      "system": {
        "type": "string",
        "description": "System prompt to embed in the model"
      },
      "template": {
        "type": "string",
        "description": "Prompt template to use for the model"
      }
    },
    "required": [
      "PCID",
      "model"
    ]
  }
  ```
</Expandable>

***

## ollama\_delete

Delete a model

**Parameters:**

| Parameter | Type   | Required | Default | Description          |
| --------- | ------ | -------- | ------- | -------------------- |
| `model`   | string | Yes      | —       | Model name to delete |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "model": {
        "type": "string",
        "description": "Model name to delete"
      }
    },
    "required": [
      "PCID",
      "model"
    ]
  }
  ```
</Expandable>

***

## ollama\_embed

Generate embeddings

**Parameters:**

| Parameter    | Type      | Required | Default | Description                                                                          |
| ------------ | --------- | -------- | ------- | ------------------------------------------------------------------------------------ |
| `dimensions` | integer   | No       | —       | Number of dimensions to generate embeddings for                                      |
| `input`      | string\[] | Yes      | —       | Text or array of texts to generate embeddings for                                    |
| `keep_alive` | string    | No       | —       | Model keep-alive duration                                                            |
| `model`      | string    | Yes      | —       | Model name                                                                           |
| `options`    | object    | No       | —       | Runtime options that control text generation                                         |
| `truncate`   | boolean   | No       | —       | If true, truncate inputs that exceed the context window. If false, returns an error. |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "dimensions": {
        "type": "integer",
        "description": "Number of dimensions to generate embeddings for"
      },
      "input": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Text or array of texts to generate embeddings for"
      },
      "keep_alive": {
        "type": "string",
        "description": "Model keep-alive duration"
      },
      "model": {
        "type": "string",
        "description": "Model name"
      },
      "options": {
        "type": "object",
        "description": "Runtime options that control text generation",
        "properties": {
          "seed": {
            "type": "integer",
            "description": "Random seed used for reproducible outputs"
          },
          "temperature": {
            "type": "number",
            "description": "Controls randomness in generation (higher = more random)"
          },
          "top_k": {
            "type": "integer",
            "description": "Limits next token selection to the K most likely"
          },
          "top_p": {
            "type": "number",
            "description": "Cumulative probability threshold for nucleus sampling"
          },
          "min_p": {
            "type": "number",
            "description": "Minimum probability threshold for token selection"
          },
          "stop": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Stop sequences that will halt generation"
          },
          "num_ctx": {
            "type": "integer",
            "description": "Context length size (number of tokens)"
          },
          "num_predict": {
            "type": "integer",
            "description": "Maximum number of tokens to generate"
          }
        }
      },
      "truncate": {
        "type": "boolean",
        "description": "If true, truncate inputs that exceed the context window. If false, returns an error."
      }
    },
    "required": [
      "PCID",
      "input",
      "model"
    ]
  }
  ```
</Expandable>

***

## ollama\_generate

Generate a response

**Parameters:**

| Parameter      | Type      | Required | Default | Description                                                                                                                                                                                                            |
| -------------- | --------- | -------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `format`       | object    | No       | —       | Structured output format for the model to generate a response from. Supports either the string `"json"` or a JSON schema object.                                                                                       |
| `images`       | string\[] | No       | —       | The images value                                                                                                                                                                                                       |
| `keep_alive`   | object    | No       | —       | Model keep-alive duration (for example `5m` or `0` to unload immediately)                                                                                                                                              |
| `logprobs`     | boolean   | No       | —       | Whether to return log probabilities of the output tokens                                                                                                                                                               |
| `model`        | string    | Yes      | —       | Model name                                                                                                                                                                                                             |
| `options`      | object    | No       | —       | Runtime options that control text generation                                                                                                                                                                           |
| `prompt`       | string    | No       | —       | Text for the model to generate a response from                                                                                                                                                                         |
| `raw`          | boolean   | No       | —       | When true, returns the raw response from the model without any prompt templating                                                                                                                                       |
| `stream`       | boolean   | No       | —       | When true, returns a stream of partial responses                                                                                                                                                                       |
| `suffix`       | string    | No       | —       | Used for fill-in-the-middle models, text that appears after the user prompt and before the model response                                                                                                              |
| `system`       | string    | No       | —       | System prompt for the model to generate a response from                                                                                                                                                                |
| `think`        | object    | No       | —       | When true, returns separate thinking output in addition to content. Can be a boolean (true/false) or a string ("high", "medium", "low", "max") for supported models, with "max" requesting the highest thinking level. |
| `top_logprobs` | integer   | No       | —       | Number of most likely tokens to return at each token position when logprobs are enabled                                                                                                                                |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "format": {
        "description": "Structured output format for the model to generate a response from. Supports either the string `\"json\"` or a JSON schema object."
      },
      "images": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "The images value"
      },
      "keep_alive": {
        "description": "Model keep-alive duration (for example `5m` or `0` to unload immediately)"
      },
      "logprobs": {
        "type": "boolean",
        "description": "Whether to return log probabilities of the output tokens"
      },
      "model": {
        "type": "string",
        "description": "Model name"
      },
      "options": {
        "type": "object",
        "description": "Runtime options that control text generation",
        "properties": {
          "seed": {
            "type": "integer",
            "description": "Random seed used for reproducible outputs"
          },
          "temperature": {
            "type": "number",
            "description": "Controls randomness in generation (higher = more random)"
          },
          "top_k": {
            "type": "integer",
            "description": "Limits next token selection to the K most likely"
          },
          "top_p": {
            "type": "number",
            "description": "Cumulative probability threshold for nucleus sampling"
          },
          "min_p": {
            "type": "number",
            "description": "Minimum probability threshold for token selection"
          },
          "stop": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Stop sequences that will halt generation"
          },
          "num_ctx": {
            "type": "integer",
            "description": "Context length size (number of tokens)"
          },
          "num_predict": {
            "type": "integer",
            "description": "Maximum number of tokens to generate"
          }
        }
      },
      "prompt": {
        "type": "string",
        "description": "Text for the model to generate a response from"
      },
      "raw": {
        "type": "boolean",
        "description": "When true, returns the raw response from the model without any prompt templating"
      },
      "stream": {
        "type": "boolean",
        "description": "When true, returns a stream of partial responses"
      },
      "suffix": {
        "type": "string",
        "description": "Used for fill-in-the-middle models, text that appears after the user prompt and before the model response"
      },
      "system": {
        "type": "string",
        "description": "System prompt for the model to generate a response from"
      },
      "think": {
        "description": "When true, returns separate thinking output in addition to content. Can be a boolean (true/false) or a string (\"high\", \"medium\", \"low\", \"max\") for supported models, with \"max\" requesting the highest thinking level."
      },
      "top_logprobs": {
        "type": "integer",
        "description": "Number of most likely tokens to return at each token position when logprobs are enabled"
      }
    },
    "required": [
      "PCID",
      "model"
    ]
  }
  ```
</Expandable>

***

## ollama\_list

List models

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

***

## ollama\_ps

List running models

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

***

## ollama\_pull

Pull a model

**Parameters:**

| Parameter  | Type    | Required | Default | Description                                 |
| ---------- | ------- | -------- | ------- | ------------------------------------------- |
| `insecure` | boolean | No       | —       | Allow downloading over insecure connections |
| `model`    | string  | Yes      | —       | Name of the model to download               |
| `stream`   | boolean | No       | —       | Stream progress updates                     |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "insecure": {
        "type": "boolean",
        "description": "Allow downloading over insecure connections"
      },
      "model": {
        "type": "string",
        "description": "Name of the model to download"
      },
      "stream": {
        "type": "boolean",
        "description": "Stream progress updates"
      }
    },
    "required": [
      "PCID",
      "model"
    ]
  }
  ```
</Expandable>

***

## ollama\_push

Push a model

**Parameters:**

| Parameter  | Type    | Required | Default | Description                                |
| ---------- | ------- | -------- | ------- | ------------------------------------------ |
| `insecure` | boolean | No       | —       | Allow publishing over insecure connections |
| `model`    | string  | Yes      | —       | Name of the model to publish               |
| `stream`   | boolean | No       | —       | Stream progress updates                    |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "insecure": {
        "type": "boolean",
        "description": "Allow publishing over insecure connections"
      },
      "model": {
        "type": "string",
        "description": "Name of the model to publish"
      },
      "stream": {
        "type": "boolean",
        "description": "Stream progress updates"
      }
    },
    "required": [
      "PCID",
      "model"
    ]
  }
  ```
</Expandable>

***

## ollama\_show

Show model details

**Parameters:**

| Parameter | Type    | Required | Default | Description                                             |
| --------- | ------- | -------- | ------- | ------------------------------------------------------- |
| `model`   | string  | Yes      | —       | Model name to show                                      |
| `verbose` | boolean | No       | —       | If true, includes large verbose fields in the response. |

<Expandable title="inputSchema">
  ```json theme={null}
  {
    "type": "object",
    "properties": {
      "PCID": {
        "type": "string",
        "description": "Pink Connect ID for the authenticated connection"
      },
      "model": {
        "type": "string",
        "description": "Model name to show"
      },
      "verbose": {
        "type": "boolean",
        "description": "If true, includes large verbose fields in the response."
      }
    },
    "required": [
      "PCID",
      "model"
    ]
  }
  ```
</Expandable>

***

## ollama\_version

Get version

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