How I Built a PDF Chat API in One Day with FastAPI, Gemini, and Qdrant

#ai #fastapi #python #rag

Have you ever wanted to just talk to a PDF instead of reading through 50 pages?

I built a full PDF Chat API in one day — upload any PDF, ask questions in natural language, and get AI-powered answers. Here's how I did it.

What it does

Upload any PDF document
Ask questions about its content in natural language
Get accurate answers powered by RAG (Retrieval Augmented Generation)
Clean web UI included — no frontend framework needed
REST API with authentication for easy integration

Tech Stack

FastAPI — REST API backend
Google Gemini — embeddings (gemini-embedding-001) + chat (gemini-2.5-flash)
Qdrant — vector database for semantic search
LangChain — RAG pipeline orchestration
Pure HTML/CSS — no React, no framework

How it works

The architecture is classic RAG in two phases:

Ingestion (upload):

Extract text from PDF
Split into chunks (1000 chars, 200 overlap)
Generate embeddings with Gemini
Store in Qdrant

Query (chat):

Embed the user's question
Search Qdrant for the 4 most relevant chunks
Send chunks + question to Gemini
Return the answer

The code

The core is surprisingly simple:

chain = (
    {"context": vector_store.as_retriever(search_kwargs={"k": 4}), 
     "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)

That's the entire RAG chain — retrieve relevant context, inject into prompt, generate answer.

What I learned

Gemini embeddings produce 3072-dimensional vectors (not 768 like older models)
grpcio on Windows can be a pain — pin to version 1.62.2
Qdrant Cloud free tier is genuinely useful for side projects
Building a clean UI in pure HTML/CSS takes less time than setting up React

Try it yourself

get the packaged version ready to deploy:
👉 https://elyassdigital.gumroad.com/l/zcgjmmz

What's next

Multi-user support with separate collections per user
Docker deployment guide
Support for other document types (Word, Excel)

Built this as a side project — happy to answer questions in the comments!

DEV Community