Process browser content

POST

/api/browser/process-content

DivinityEngine - Local development
DivinityEngine - Localhost alternative

Acknowledge receipt of browser content for future processing.

Accepts webpage content metadata. Currently returns an acknowledgment; actual AI analysis is performed on-demand via the /analyze endpoint.

Request Body^required

BrowserContentRequest

Request model for browser content processing.

Used for submitting webpage content to the browser processing system for AI analysis, storage, and semantic indexing in ChromaDB.

Fields:

title: The page title for identification
url: The webpage URL for reference
content: The main text content of the page
meta: Additional page metadata (headers, tags, etc.)
project: Project context for organization
word_count: Number of words in the content
extracted_at: ISO timestamp of content extraction

Metadata Structure:

{
  "author": "John Doe",
  "published": "2024-12-20",
  "tags": ["technical", "tutorial"],
  "description": "Page meta description"
}

Usage: POST /api/browser/process-content for ingesting webpage content.

JSON Example:

{
  "title": "TypeScript Best Practices",
  "url": "https://example.com/typescript-guide",
  "content": "TypeScript is a typed superset of JavaScript...",
  "meta": {"author": "Tech Writer", "tags": ["typescript", "tutorial"]},
  "project": "ishvana_docs",
  "wordCount": 1500,
  "extractedAt": "2024-12-20T10:30:00Z"
}

Integration:

Browser Service: Processes and stores content
ChromaDB: Indexes content for semantic search
AI Analysis: Extracts entities and generates summaries
Frontend Extension: Sends content from browser

object

title

required

Title

Page title

string

url

required

Url

Page URL

string format: uri

>= 1 characters <= 2083 characters

content

required

Content

Page text content

string

meta

Page metadata

object

key

additional properties

any

project

Project

Project context

string

default: general

wordCount

Wordcount

Word count

integer

extractedAt

required

Extractedat

Extraction timestamp

string

Responses

200

Successful Response

BrowserAutomationResponse

Generic response model for browser automation endpoints.

Flexible response structure for browser automation operations including content processing, bookmark retrieval, and automation status responses. All fields are optional to support different endpoint response formats while maintaining type safety.

Fields:

status: Operation status (e.g., “processing”, “success”, “deleted”)
message: Human-readable message about the operation
url: Related URL (for content processing endpoints)
title: Related page title (for content processing endpoints)
bookmarks: List of bookmark objects (for bookmark retrieval endpoints)
total: Count of returned items (for listing endpoints)
filters: Dictionary containing applied filter values (for query endpoints)
bookmark_id: Bookmark identifier (for deletion endpoints)

Usage: Used across multiple browser automation endpoints:

POST /api/browser/process-content: Returns status, message, url, title
GET /api/browser/bookmarks: Returns bookmarks, total, filters
DELETE /api/browser/bookmarks/{bookmark_id}: Returns status, bookmark_id

JSON Example (Content Processing):

{
  "status": "processing",
  "message": "Content queued for AI analysis",
  "url": "https://example.com/page",
  "title": "Example Page"
}

JSON Example (Bookmark Listing):

{
  "bookmarks": [
    {
      "id": "bookmark_123",
      "url": "https://example.com",
      "title": "Example Page",
      "project": "research"
    }
  ],
  "total": 1,
  "filters": {"project": "research", "tag": null, "limit": 50}
}

JSON Example (Bookmark Deletion):

{
  "status": "deleted",
  "bookmarkId": "bookmark_123"
}

object

status

Any of:

string
null

string

message

Any of:

string
null

string

url

Any of:

string
null

string

title

Any of:

string
null

string

bookmarks

Any of:

Array<object>
null

Array<object>

BookmarkResponse

Response model for bookmark creation results - COMPLETE BOOKMARK DATA.

Contains the complete bookmark including all user-provided data, AI-generated tags, summary, and usage suggestions for knowledge organization. This is the SINGLE SOURCE OF TRUTH for bookmark structure - frontend consumes this schema.

Fields:

bookmark_id: Unique identifier for the bookmark
url: Bookmarked URL
title: Page title
content: Page content
category: Bookmark category (research/reference/documentation/inspiration/other)
description: User-provided description or notes
project: Project context
user_tags: User-defined tags
ai_tags: AI-generated tags for categorization
ai_summary: AI-generated summary of the content
suggestions: AI-generated suggestions for usage
created_at: ISO 8601 timestamp of bookmark creation

AI Tags: Generated based on content analysis, typically 3-7 tags capturing:

Primary topics
Technologies mentioned
Content type (tutorial, reference, etc.)
Difficulty level

AI Summary: 2-3 sentence summary of bookmark content and utility.

Suggestions: Actionable recommendations like:

“Use for React performance optimization reference”
“Apply patterns to Ishvana frontend components”
“Share with team for TypeScript best practices”

Usage: Returned from POST /api/browser/bookmark endpoint.

JSON Example:

{
  "bookmarkId": "bm_abc123",
  "url": "https://example.com/typescript-guide",
  "title": "TypeScript Best Practices",
  "content": "TypeScript is a typed superset...",
  "category": "documentation",
  "description": "Comprehensive guide to TypeScript best practices",
  "project": "ishvana_docs",
  "userTags": ["typescript", "reference"],
  "aiTags": ["typescript", "best-practices", "type-safety", "tutorial"],
  "aiSummary": "Comprehensive guide to TypeScript best practices focusing on "
    "type safety and modern patterns",
  "suggestions": [
    "Apply type narrowing patterns to Ishvana codebase",
    "Use as reference for strict TypeScript configuration",
    "Share with development team"
  ],
  "createdAt": "2024-12-20T10:30:00Z"
}

object

bookmarkId

required

Bookmarkid

Unique bookmark identifier

string

url

required

Url

Bookmarked URL

string

title

required

Title

Page title

string

content

required

Content

Page content

string

category

required

Category

Bookmark category

string

description

required

Description

User-provided description or notes

string

project

required

Project

Project context

string

userTags

Usertags

User-defined tags

Array<string>

aiTags

Aitags

AI-generated tags

Array<string>

aiSummary

Any of:

string
null

string

suggestions

Suggestions

Usage suggestions

Array<string>

createdAt

required

Createdat

ISO 8601 bookmark creation timestamp

string

contentAnalysis

Any of:

Array<object>
null

Array<object>

ContentAnalysisResponse

Response model for content analysis results.

Contains the structured results of AI-powered content analysis including summary, key points, entities, and relevance scoring.

Fields:

summary: Concise summary of the content
key_points: List of important points extracted
entities: List of important entities mentioned
project_relevance: Analysis of relevance to the project
reading_time: Estimated reading time
content_type: Type of content analyzed
analysis_timestamp: When the analysis was performed
word_count: Number of words in the original content

Summary Format: 2-3 sentence concise summary capturing main points and purpose.

Key Points Format: Bullet-point style extractive summary (5-10 points for long content).

Entities Examples:

React, TypeScript, Webpack (technologies)
Facebook, Microsoft (organizations)
Dan Abramov, Kent C. Dodds (people)

Project Relevance: Explanation of why content is useful for the current project with specific use case recommendations.

Reading Time: Human-readable format: “5 minutes”, “15 minutes”, “1 hour”

Content Types:

webpage: General webpage
tutorial: Step-by-step tutorial
documentation: Technical documentation
blog_post: Blog or article
research_paper: Academic or research content
news: News article

Usage: Returned from POST /api/browser/analyze endpoint.

JSON Example:

{
  "summary": "Guide to optimizing React performance using memoization and virtualization",
  "keyPoints": [
    "Use React.memo for expensive components",
    "Implement virtualization for long lists",
    "Optimize re-renders with useMemo"
  ],
  "entities": ["React", "useMemo", "React.memo", "virtualization"],
  "projectRelevance": "Directly applicable to Ishvana frontend optimization",
  "readingTime": "8 minutes",
  "contentType": "tutorial",
  "analysisTimestamp": "2024-12-20T10:30:00Z",
  "wordCount": 2000
}

object

summary

Any of:

string
null

string

keyPoints

Keypoints

Extracted key points

Array<string>

entities

Entities

Important entities

Array<string>

projectRelevance

Any of:

string
null

string

readingTime

Any of:

string
null

string

contentType

Contenttype

Content type

string

default: webpage

analysisTimestamp

required

Analysistimestamp

Analysis timestamp

string

wordCount

required

Wordcount

Word count

integer

recentAnalysis

Any of:

Array<object>
null

Array<object>

ContentAnalysisResponse

Response model for content analysis results.

Contains the structured results of AI-powered content analysis including summary, key points, entities, and relevance scoring.

Fields:

summary: Concise summary of the content
key_points: List of important points extracted
entities: List of important entities mentioned
project_relevance: Analysis of relevance to the project
reading_time: Estimated reading time
content_type: Type of content analyzed
analysis_timestamp: When the analysis was performed
word_count: Number of words in the original content

Summary Format: 2-3 sentence concise summary capturing main points and purpose.

Key Points Format: Bullet-point style extractive summary (5-10 points for long content).

Entities Examples:

React, TypeScript, Webpack (technologies)
Facebook, Microsoft (organizations)
Dan Abramov, Kent C. Dodds (people)

Project Relevance: Explanation of why content is useful for the current project with specific use case recommendations.

Reading Time: Human-readable format: “5 minutes”, “15 minutes”, “1 hour”

Content Types:

webpage: General webpage
tutorial: Step-by-step tutorial
documentation: Technical documentation
blog_post: Blog or article
research_paper: Academic or research content
news: News article

Usage: Returned from POST /api/browser/analyze endpoint.

JSON Example:

{
  "summary": "Guide to optimizing React performance using memoization and virtualization",
  "keyPoints": [
    "Use React.memo for expensive components",
    "Implement virtualization for long lists",
    "Optimize re-renders with useMemo"
  ],
  "entities": ["React", "useMemo", "React.memo", "virtualization"],
  "projectRelevance": "Directly applicable to Ishvana frontend optimization",
  "readingTime": "8 minutes",
  "contentType": "tutorial",
  "analysisTimestamp": "2024-12-20T10:30:00Z",
  "wordCount": 2000
}

object

summary

Any of:

string
null

string

keyPoints

Keypoints

Extracted key points

Array<string>

entities

Entities

Important entities

Array<string>

projectRelevance

Any of:

string
null

string

readingTime

Any of:

string
null

string

contentType

Contenttype

Content type

string

default: webpage

analysisTimestamp

required

Analysistimestamp

Analysis timestamp

string

wordCount

required

Wordcount

Word count

integer

total

Any of:

integer
null

integer

filters

Any of:

object
null

object

key

additional properties

Any of:

string

bookmarkId

Any of:

string
null

string

categoryId

Any of:

string
null

string

422

Validation Error

HTTPValidationError

object

detail

Detail

Array<object>

ValidationError

object

loc

required

Location

Array

msg

required

Message

string

type

required

Error Type

string

input

Input

ctx

Context

object

Process browser content

Request Body required

Responses

200

422

Request Body^required