Deep Research turns a question into a structured, magazine-quality report by having the LLM drive every decision in a multi-step iterative loop. Adapted from Tongyi DeepResearch (Alibaba), it goes far beyond a single web search: it plans a research strategy, generates targeted queries, fetches and reads sources, synthesizes findings into an evolving report, and decides when it has enough coverage — all autonomously.Documentation Index
Fetch the complete documentation index at: https://mintlify.com/pewdiepie-archdaemon/odysseus/llms.txt
Use this file to discover all available pages before exploring further.
How it works
Deep Research runs the following loop for up to the configured number of rounds:Plan
The LLM analyzes your question and creates a research plan: a list of sub-questions to investigate, key topics to cover, and a success criterion describing what a complete answer looks like.
Think — generate queries
Based on the plan and what has been gathered so far, the LLM generates 3–4 focused search queries for this round. Later rounds generate targeted follow-up queries to fill gaps identified in earlier synthesis.
Search
All queries for the round run in parallel against the configured search provider (SearXNG by default). Top result URLs are collected, deduplicating URLs already visited.
Extract
Each URL is fetched and its content is passed to the LLM for extraction. The model identifies evidence relevant to the original question and returns a structured summary with source URL and title. Concurrency is bounded to avoid overwhelming a local model server.
Synthesize
The LLM integrates all new findings into the evolving report — removing redundancy, resolving contradictions, maintaining logical flow, and keeping inline source citations.
Research categories
Deep Research auto-detects the type of question and adapts the report format:| Category | Format |
|---|---|
| product | Ranked list with pros/cons, prices, and a Verdict section |
| comparison | Comparison table plus per-option sections and “Best For” verdicts |
| howto | Quick guide, prerequisites, numbered steps, and Common Mistakes |
| factcheck | Evidence For / Against, Verdict, and Nuance & Caveats sections |
| general | Free-form narrative with headings and inline citations |
Output
Completed reports appear in the Deep Research sidebar and are saved permanently in the Library. Each report includes:- The full structured report with
##section headings - Inline source citations as clickable links
- A source list with titles and URLs
- Research statistics (rounds completed, sources read, queries run, model used, elapsed time)
Configuration
Research uses the model configured in Settings → Research Model. If no research-specific model is set, it falls back to the session model. Key parameters (configurable in Settings):| Setting | Description | Default |
|---|---|---|
| Research model | Model used for all research LLM calls | Session default |
| Max rounds | Maximum search-extract-synthesize cycles | 8 |
| Max time | Wall-clock time limit for the full run | 300 s |
| Max URLs per round | Sources fetched per round | 3 |
| Search provider | Provider for research queries (separate from chat search) | SearXNG |
Starting a research job
You can start a Deep Research job three ways:- From the Deep Research panel — click New Research, type your question, and click Start.
- From Agent mode — say “research X” or “do a deep dive on Y” and the agent calls
trigger_researchautomatically, opening the live progress view. - From the API —
POST /api/research/startwith{ "query": "..." }.
Deep Research requires a working web search provider. The bundled Docker Compose stack includes SearXNG on port 8080 and wires it automatically. For native installs, configure SearXNG in Settings → Search. See SearXNG Integration.