Knowledge Base
Turn Engram into a domain expert. Crawls external documentation sites, vectorizes the content into the local Qdrant doc_knowledge collection, and answers complex questions with citation-backed accuracy.
Intelligently traverses documentation pages, respecting domain boundaries and separating code blocks from prose.
Uses Qdrant's doc_knowledge collection to store 768-dimensional embeddings on your disk. No data ever leaves your machine.
Retrieval-Augmented Generation fetches the exact documentation snippet needed to ground the AI's answer.
Interface Options
Engram provides two ways to interact with your knowledge base: a visual dashboard for ease of use, and a CLI tool for automation.
@app.route() decorator.# Example
@app.route("/")
def hello():
return "Hello World"
Technical Setup
01Install Dependencies
The crawler requires specific Python libraries for scraping and vector storage. Ensure these are in your backend container.
beautifulsoup4
requests
qdrant-client02Git Exclusion
Qdrant data lives in a Docker named volume and never appears as a local directory. If you run Qdrant outside Docker during development, exclude any local data directories from version control.
# .gitignore — add if running Qdrant locally outside Docker
qdrant_storage/