# Chat with document

- Human page: https://happytails.ai/en/document-tools/chat-with-document/
- Markdown: https://happytails.ai/en/document-tools/chat-with-document.md
- Structured JSON: https://happytails.ai/agents/en/document-tools/chat-with-document/index.json
- Visibility: public

## Tool capabilities

| Property | Value |
| --- | --- |
| Tool ID | `chat-with-document` |
| Category | document-tools |
| Implementation | Registered implementation. Registration alone is not a production-quality guarantee. |
| Browser execution | Use the visible action or interactive controls. |
| Browser processing | Server required |
| HTTP API | /api/v1/tools/chat-with-document/run |
| Browser-agent interface | run_current_tool |

### Implementation notes

Runs with local model weights on this website’s server. No external AI API is used. Review the result for errors. Answers from one uploaded document per request. No persistent index or chat history is stored. Source limited to 16,000 characters.

### Inputs and settings

No free-text input is required. Use the file inputs and/or settings below.

Accepted browser files: `.pdf,.docx,.txt`. Choose one file.

Browser file-input limit: 20971520 bytes in total. HTTP limits can differ.

| Setting | Meaning | Control type | Default | Constraints |
| --- | --- | --- | --- | --- |
| `question` | Your question | text | "" |  |

### HTTP contract

API calls process supplied data on the server. The website origin is `https://happytails.ai`. Server API hosting is not connected on the public website yet. Use your local server origin to test these requests.

```http
POST https://happytails.ai/api/v1/tools/chat-with-document/run
Content-Type: application/json
```

[Detailed operation reference](https://happytails.ai/en/api/tools/chat-with-document.md) · [Shared API guide](https://happytails.ai/en/api.md)

#### Limits

| Limit | Value |
| --- | --- |
| request_bytes | 31457280 |
| input_characters | 1000000 |
| files_bytes | 20971520 |
| max_files | 1 |
| timeout_seconds | 90 |

#### Complete input schema

```json
{
  "type": "object",
  "additionalProperties": false,
  "properties": {
    "input": {
      "type": "string",
      "maxLength": 1000000,
      "default": "",
      "description": "Plain text input. File tools use files instead unless otherwise documented."
    },
    "options": {
      "type": "object",
      "additionalProperties": false,
      "properties": {
        "question": {
          "type": "string",
          "description": "Your question",
          "default": ""
        }
      }
    },
    "files": {
      "type": "array",
      "maxItems": 1,
      "items": {
        "type": "object",
        "required": [
          "name",
          "base64"
        ],
        "additionalProperties": false,
        "properties": {
          "name": {
            "type": "string",
            "maxLength": 200,
            "description": "Filename only, no path."
          },
          "mime": {
            "type": "string",
            "maxLength": 150
          },
          "bytes": {
            "type": "integer",
            "minimum": 0,
            "description": "Optional decoded byte count; must match content if supplied."
          },
          "base64": {
            "type": "string",
            "contentEncoding": "base64",
            "description": "File bytes as padded base64. Use the tool-specific limits.files_bytes value for the total decoded input size."
          }
        }
      }
    }
  }
}
```

#### Complete output schema

```json
{
  "type": "object",
  "required": [
    "tool",
    "result"
  ],
  "properties": {
    "tool": {
      "type": "string"
    },
    "result": {
      "type": "object",
      "required": [
        "text",
        "files"
      ],
      "properties": {
        "text": {
          "type": [
            "string",
            "null"
          ]
        },
        "data": {
          "description": "Parsed JSON when the textual result is JSON."
        },
        "name": {
          "type": "string"
        },
        "mime": {
          "type": "string"
        },
        "files": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "name",
              "mime",
              "bytes",
              "base64"
            ],
            "properties": {
              "name": {
                "type": "string"
              },
              "mime": {
                "type": "string"
              },
              "bytes": {
                "type": "integer"
              },
              "base64": {
                "type": "string",
                "contentEncoding": "base64"
              }
            }
          }
        }
      }
    }
  }
}
```

#### Error and retry handling

Failures return a non-200 status and `error.code` plus `error.message`. Correct invalid input before retrying; retry server-busy responses with bounded backoff. Returned files contain Base64 data, not persistent download URLs. Decode and inspect the output before treating conversion as successful. See the shared API guide for the complete status and timeout rules.

### Browser-agent workflow

1. Open the human page in a browser that supports WebMCP.
2. Discover the interface exposed by that page; use its actual schema.
3. Select files on the page first when the tool requires files.
4. Call `run_current_tool` with valid input and settings.
5. Inspect the returned result or error and the displayed output. Retrieve files from the displayed download links.

Calls do not automatically copy or download results. Browser permissions still apply. Interface availability alone is not proof of successful execution.

### Planning specification

Answer questions over an uploaded document with quoted passages and page links; show insufficient-evidence responses; delete session index on request; resist instructions embedded in documents.

This describes intended requirements. Use the implementation notes, interface schema and observed output to determine current support.

### Complete machine-readable capability record

```json
{
  "id": "chat-with-document",
  "category": "document-tools",
  "built": true,
  "requirements": "Answer questions over an uploaded document with quoted passages and page links; show insufficient-evidence responses; delete session index on request; resist instructions embedded in documents.",
  "implementation": {
    "fields": [
      {
        "key": "question",
        "label": "Your question",
        "type": "text",
        "value": ""
      }
    ],
    "files": true,
    "accept": ".pdf,.docx,.txt",
    "multiple": false,
    "input": false,
    "processing": "Server required",
    "native": true,
    "ai": true,
    "maxFileBytes": 20971520,
    "note": "Runs with local model weights on this website’s server. No external AI API is used. Review the result for errors. Answers from one uploaded document per request. No persistent index or chat history is stored. Source limited to 16,000 characters.",
    "experience": {
      "automatic": false,
      "single": false,
      "label": "Your text",
      "placeholder": "Type or paste your input…",
      "help": "Up to 1,000,000 characters. Review the settings before running.",
      "action": null
    },
    "mode": "explicit",
    "interactive": false
  },
  "execution": "POST /api/v1/tools/chat-with-document/run",
  "api": {
    "id": "chat-with-document",
    "name": "Chat with document",
    "category": "document-tools",
    "description": "Ask a question about the text in a document.",
    "notes": "Runs with local model weights on this website’s server. No external AI API is used. Review the result for errors. Answers from one uploaded document per request. No persistent index or chat history is stored. Source limited to 16,000 characters.",
    "human_path": "/en/document-tools/chat-with-document/",
    "method": "POST",
    "endpoint": "/api/v1/tools/chat-with-document/run",
    "schema_url": "/api/v1/tools/chat-with-document",
    "input_schema": {
      "type": "object",
      "additionalProperties": false,
      "properties": {
        "input": {
          "type": "string",
          "maxLength": 1000000,
          "default": "",
          "description": "Plain text input. File tools use files instead unless otherwise documented."
        },
        "options": {
          "type": "object",
          "additionalProperties": false,
          "properties": {
            "question": {
              "type": "string",
              "description": "Your question",
              "default": ""
            }
          }
        },
        "files": {
          "type": "array",
          "maxItems": 1,
          "items": {
            "type": "object",
            "required": [
              "name",
              "base64"
            ],
            "additionalProperties": false,
            "properties": {
              "name": {
                "type": "string",
                "maxLength": 200,
                "description": "Filename only, no path."
              },
              "mime": {
                "type": "string",
                "maxLength": 150
              },
              "bytes": {
                "type": "integer",
                "minimum": 0,
                "description": "Optional decoded byte count; must match content if supplied."
              },
              "base64": {
                "type": "string",
                "contentEncoding": "base64",
                "description": "File bytes as padded base64. Use the tool-specific limits.files_bytes value for the total decoded input size."
              }
            }
          }
        }
      }
    },
    "output_schema": {
      "type": "object",
      "required": [
        "tool",
        "result"
      ],
      "properties": {
        "tool": {
          "type": "string"
        },
        "result": {
          "type": "object",
          "required": [
            "text",
            "files"
          ],
          "properties": {
            "text": {
              "type": [
                "string",
                "null"
              ]
            },
            "data": {
              "description": "Parsed JSON when the textual result is JSON."
            },
            "name": {
              "type": "string"
            },
            "mime": {
              "type": "string"
            },
            "files": {
              "type": "array",
              "items": {
                "type": "object",
                "required": [
                  "name",
                  "mime",
                  "bytes",
                  "base64"
                ],
                "properties": {
                  "name": {
                    "type": "string"
                  },
                  "mime": {
                    "type": "string"
                  },
                  "bytes": {
                    "type": "integer"
                  },
                  "base64": {
                    "type": "string",
                    "contentEncoding": "base64"
                  }
                }
              }
            }
          }
        }
      }
    },
    "processing": "Server; self-hosted native engine, no external conversion service",
    "limits": {
      "request_bytes": 31457280,
      "input_characters": 1000000,
      "files_bytes": 20971520,
      "max_files": 1,
      "timeout_seconds": 90
    }
  },
  "agent_processing": "Server; self-hosted native engine, no external conversion service",
  "browser_agent": {
    "supported": true,
    "name": "run_current_tool",
    "discovery": "WebMCP on the human page in a supporting browser",
    "verification": "See audit/API-AUDIT.md; availability is not verification"
  }
}
```

## Page guide

Ask a question about the text in a document.

## Useful next steps

- [Document summarizer](https://happytails.ai/en/document-tools/document-summarizer/): Summarize readable document text with source references. ([Markdown](https://happytails.ai/en/document-tools/document-summarizer.md))

- [OCR PDF](https://happytails.ai/en/pdf-tools/ocr-pdf/): Add searchable English text to scanned PDF pages. ([Markdown](https://happytails.ai/en/pdf-tools/ocr-pdf.md))

## How to use Chat with document

1. Choose a file in PDF, DOCX or TXT.
2. Review the settings, then choose Run Chat with document.
3. Review the result, then use Copy result or a download link when available.

## What to expect

Ask a question about the text in a document. Runs with local model weights on this website’s server. No external AI API is used. Review the result for errors. Answers from one uploaded document per request. No persistent index or chat history is stored. Source limited to 16,000 characters.