GPT Researcher

Orchestrates parallel web searches across multiple sources (Google, Bing, DuckDuckGo, Tavily API) by using an LLM to decompose research topics into targeted sub-queries, then aggregates and deduplicates results. Implements a query expansion loop where the LLM analyzes initial results to identify information gaps and generates follow-up searches, creating a depth-first research graph rather than simple keyword matching.

Aggregates raw search results into a structured research report by using an LLM to synthesize information across sources, organize findings by topic hierarchy, and maintain inline citations linking each claim to its source URL. Implements a two-pass approach: first pass clusters results by semantic similarity, second pass generates report sections with citation metadata embedded in the output structure.

Provides a unified interface to multiple LLM providers (OpenAI, Anthropic, Ollama, local models, Azure OpenAI) with automatic provider selection based on cost, latency, or capability requirements. Implements a provider registry pattern where each provider exposes a standardized interface, and the orchestrator selects the optimal provider for each task (e.g., cheap model for query generation, expensive model for synthesis).

Breaks down a research request into subtasks (query generation, search execution, result aggregation, synthesis) and executes them in dependency order using an async task graph. Each task is a node with input/output contracts, and the executor resolves dependencies and parallelizes independent tasks. Implements a DAG (directed acyclic graph) pattern where task outputs feed into downstream tasks, enabling efficient resource utilization and resumable execution.

Allows users to specify research parameters (number of search iterations, result limit per query, report length, focus areas) that control the breadth and depth of investigation. Implements a configuration object that propagates through the task graph, affecting query generation (how many follow-up queries), search execution (how many results to fetch), and synthesis (report length and detail level).

Fetches full HTML content from search result URLs and extracts relevant text using HTML parsing and optional LLM-based content filtering. Implements a scraper that handles common web page structures (articles, blog posts, documentation) and filters out boilerplate (navigation, ads, comments) to extract the core content. Uses BeautifulSoup or similar for parsing, with optional LLM post-processing to identify relevant sections.

Caches research results and intermediate outputs (search results, synthesis) to avoid redundant API calls and LLM invocations when the same topic is researched multiple times. Implements a simple file-based or database cache keyed by research topic hash, with optional TTL (time-to-live) to refresh stale results. Enables resumable research where a failed job can pick up from the last completed task.

Generates research reports in multiple formats (markdown, JSON, HTML, plain text) using template-based rendering. Implements a template system where each format has a corresponding template that defines structure, styling, and citation formatting. Supports custom templates for domain-specific report structures (e.g., competitive analysis, market research, technical documentation).

Evaluates research quality by analyzing source diversity, information consensus, and claim support. Implements heuristics that score research based on number of independent sources per claim, agreement between sources, and recency of information. Produces a confidence score (0-100) for the overall research and per-section confidence metrics.

Automatically discovers related topics and subtopics by analyzing search results and using LLM to identify conceptual relationships. Implements a topic graph where nodes are topics and edges represent relationships (e.g., 'is-a', 'related-to', 'causes'). Enables users to expand research scope by following topic relationships or narrow scope by focusing on specific subtopics.