ProjectsSeptember 29, 2026

Document Q&A with Django and pgvector

View source
Built with
  • Django
  • Django REST Framework
  • PostgreSQL
  • pgvector
  • Gemini 2.5 Flash
Document Q&A with Django and pgvector: illustrated cover

System architecture

Component and data flow diagramCSV Q&A pairs to Gemini embeddings: Batch text. Gemini embeddings to PostgreSQL: Store vectors. Question endpoint to Retrieval service: Embed query. Retrieval service to PostgreSQL: Vector search. Retrieval service to RAG service: Relevant context.INGESTION ABOVE / QUESTION ANSWERING BELOWBatch textStore vectorsEmbed queryVector searchRelevant contextCSV Q&A pairsIngestion serviceGemini embeddings768-dimensional vectorsPostgreSQLpgvector + source dataQuestion endpointQuery + categoryRetrieval serviceCosine similarityRAG serviceGemini / fallback
Swipe horizontally to inspect the diagram.Retrieval applies category and similarity filters. With no relevant context, the service returns a fallback instead of asking the model for an unsupported answer.

The problem

A general language model does not automatically know the contents of a private dataset. This backend makes stored Q&A pairs searchable by meaning, then supplies matching text as context for generation. It is a separate project from the multilingual, multi-tenant RAG engine.

Architecture

The ingestion service validates CSV columns, formats question-and-answer rows, requests Gemini embeddings in batches and stores content, source, category and vectors in PostgreSQL through Django models. Failed embedding batches are logged and counted as skipped. At query time, the retrieval service embeds the question using the same embedding path. A pgvector cosine-distance query orders candidates, optionally filters by category and keeps candidates within a relevance threshold. The RAG service builds a prompt from that context and calls Gemini for the answer. If nothing meets the retrieval threshold, it returns a fallback without making the generation call. REST views expose query, ingest and health operations. Model names, dimensions, thresholds and retry settings live in configuration rather than being repeated throughout the services.

Trade-offs

pgvector keeps content and vectors in the same database. This reduces the number of services to operate, but vector indexing and retrieval quality still need workload-specific measurement. Using a hosted embedding API simplifies local infrastructure while adding external latency, quotas and a data-processing dependency. A relevance threshold helps reject weak context; it cannot guarantee hallucination-free answers. The threshold needs evaluation against representative questions, including questions the dataset cannot answer.

Current result and next steps

The repository documents authentication as unfinished and the Celery task as a disabled stub. Ingestion is therefore described here as a synchronous prototype. Before exposing it publicly I would require authentication, bound upload size, verify safe replacement on partial embedding failures and build a retrieval evaluation set. No production latency or accuracy is claimed for this project.

Source code

Related projects

Algorithms in Python and Java: illustrated coverExplore project ↗
Learning project

Algorithms in Python and Java

Understand how data structures and algorithm choices change the cost of solving a problem.

Result & scope
A public learning collection covering graphs, dynamic programming, trees, searching and more.
  • Python
Read case study View source
Bookstore: catalogue, cart and orders: illustrated coverExplore project ↗
Personal prototype

Bookstore: catalogue, cart and orders

Connect a browsable book catalogue to a shopping cart and persisted orders.

Result & scope
An e-commerce prototype with server-calculated order totals; authentication remains unfinished.
  • React
  • Node.js
  • MongoDB
Read case study View source

Let’s talk about the engineering

I’m open to software engineering roles across backend, platform, and data teams. Get in touch to discuss the architecture, trade-offs, or how this experience could help your team.
Get in touch