search

brain-circuitDeep Research

hashtag
Overview

GLChat DeepResearch is an experience-layer pipeline in the GLChat backend that provides deep research capabilities to users. It handles user-facing behavior, profile management, and result presentation for deep research queries.

hashtag
Key Features

  1. Profile-Based Research: Three user-facing profiles (Essentials, Comprehensive, Internal)

  2. Intelligent Routing: Automatically determines if deep research is needed

  3. Automatic Fallback: Comprehensive → Essentials when quota exceeded

  4. Streaming Support: Real-time progress and results

  5. Multi-tenancy: Full organization-level isolation

  6. Citation Formatting: Structured references for UI display

hashtag
Architecture Context

  1. GLChat DeepResearch (this document) — Experience-layer pipeline that defines product behavior

  2. GL SDK DeepResearcher — Library-level SDK abstraction for backend-agnostic deep research (see GL SDK DeepResearcher docsarrow-up-right)

This document focuses on GLChat DeepResearch and how to use it in the GLChat backend.

PreviousAgentic PipelineNextWhat is GLChat DeepResearch?

Last updated