RAG Workflows

RAG Workflows

Retrieval-Augmented Generation (RAG) in ADEPT enables agents to answer questions grounded in your uploaded documents. The platform uses a ChromaDB/pgvector hybrid vector store with visibility-scoped collections to control access.

Overview

The RAG pipeline follows three stages:

1. Upload -- Files are ingested into session-scoped storage.
2. Process -- Documents are chunked, embedded, and indexed into a vector collection.
3. Query -- The agent retrieves relevant chunks and uses an LLM to synthesize an answer.

Uploading Files

curl -X POST https://your-adept-server.example.com/v1/files \
  -H "Authorization: Bearer $TOKEN" \
  -F "file=@dataset.csv" \
  -F "purpose=assistants"

Supported file types include CSV, PDF, and plain text files.

Processing Types

Processing Type	Description	Use Case
auto	Automatic detection based on file extension	General-purpose ingestion
rag	Full RAG pipeline (chunk, embed, index)	Document Q&A
sql	Convert to SQL-queryable tables	Structured data analysis
dataframe	Load as pandas DataFrame	Statistical operations
text	Raw text extraction	Simple text retrieval

Creating RAG Indexes

Use create_rag_index_from_folder to index multiple files at once:

Agent, create a RAG index from my uploaded folder with user-level visibility.

The tool accepts a timeout_seconds parameter for large batch operations and a visibility parameter to control who can access the resulting collection.

Querying Documents

Agent, what are the key findings in my uploaded research paper?

The LLM synthesizes answers grounded in retrieved context, citing relevant passages when possible.

Visibility Scoping

Collections are scoped using a naming convention that controls access:

Scope	Collection Naming	Access
Session (default)	s_{session_id[:12]}_{name}	Current MCP session only
User	u_{owner_id[:12]}_{name}	Persists across sessions for the owning user
World	w_{name}	Accessible to any authenticated user

Choosing Visibility: Use session for ephemeral exploration, user for personal knowledge bases that persist across conversations, and world for shared organizational resources.

Batch Operations

process_files_batch

Processes multiple files in parallel with configurable concurrency. Uses per-session locking to prevent concurrent metadata corruption.

create_rag_index_from_folder

Creates a unified RAG index from all files in a session folder with support for visibility and timeout_seconds parameters.

Vector Store Backend

ADEPT uses ChromaDB as the primary vector store:

• Production: HttpClient connecting to a dedicated ChromaDB service
• Fallback: PersistentClient for local development without a ChromaDB server
• Embeddings: Configurable via EMBEDDING_DEFAULT_MODEL environment variable

The BackendFactory selects the appropriate backend based on the backend_type configuration parameter.