A Single-Agent Customer Support RAG System (FastAPI + LangChain + Groq + Chroma + Streamlit)

---

✅ 1. Problem We Are Solving

Modern customer support teams deal with:

• Large PDF manuals (device manuals, onboarding guides, support documentation)

• Repetitive questions (“How to reset?”, “Battery issue?”, “Warranty?”)

• Delays in retrieving the correct answer

• High dependency on support staff expertise

Goal:
Automate customer support by allowing users to:

📄 Upload their product manuals (PDFs)
❓ Ask natural-language questions
🤖 Receive accurate, contextual answers powered by RAG (Retrieval-Augmented Generation)

This reduces support load and improves response quality.

---

✅ 2. High-Level Solution

We build a single-agent RAG system:

1. User uploads a PDF

2. System extracts text + chunks + embeds

3. Chunks stored in ChromaDB

4. User asks a question

5. System retrieves relevant chunks

6. Groq LLM generates the answer using retrieved context

The agent does not use multi-agent coordination —
Instead, it performs the full RAG workflow independently.

---

✅ 3. Architecture Overview

                   ┌──────────────────────────┐
                   │       Streamlit UI       │
                   │  - Upload PDF            │
                   │  - Ask question          │
                   └────────────┬─────────────┘
                                │
                                ▼
                       (FastAPI Backend)
          ┌─────────────────────────────────────────┐
          │ 1. PDF Loader (PyPDF)                   │
          │ 2. Text Splitter                        │
          │ 3. Embeddings (HuggingFace)             │
          │ 4. Vector Store (ChromaDB)              │
          │ 5. Retriever (LangChain)                │
          │ 6. Groq LLM (Llama models)              │
          └─────────────────────────────────────────┘
                                │
                                ▼
                   ┌──────────────────────────┐
                   │    Final Answer (RAG)    │
                   │ Retrieved Chunks + LLM   │
                   └──────────────────────────┘

---

✅ 4. Technical Implementation

4.1 Backend — FastAPI

Responsibilities:

• Accept PDF uploads

• Convert PDF → raw text

• Split text into chunks

• Convert chunks → embeddings

• Store embeddings in Chroma

• Handle user queries

• Perform retrieval + LLM answer generation

Key Components:

Component	Purpose
PyPDF2	PDF → text extraction
RecursiveCharacterTextSplitter	Splits into meaningful chunks
HuggingFaceEmbeddings	Embedding generation
Chroma	Vector store for retrieval
Groq LLM	Generates the final answer
LangChain Retrieval Pipeline	Glue connecting all steps

---

4.2 RAG Flow (Backend)

✅ Indexing Step (after PDF upload)

PDF → Text → Chunks → Embeddings → ChromaDB

✅ Query Step (user question)

Question → Retrieve Top Chunks → LLM (Groq) → Answer

---

4.3 UI — Streamlit

Responsibilities:

• PDF upload

• Send file to backend

• Question textbox

• Display final LLM answer

Ideal for rapid prototyping and demos.

---

✅ 5. Environment Setup 

Download code from : https://github.com/kkvinodkumaran/support_rag_single_agent 

Create a .env file in the project root:

GROQ_API_KEY=gsk_xxx
MODEL_NAME=llama-3.1-8b-instant

Note
Get Groq API key from https://console.groq.com
Get Tavily API key (optional) from https://tavily.com

 

---

✅ 6. Running the System

6.1 Run using Docker Compose (recommended)

From the project root:

docker compose up --build

Access:

• Backend API Docs: http://localhost:8000/docs

• Streamlit UI: http://localhost:8501

---

✅ 7. Local Development (uv)

Backend

cd backend
uv sync
GROQ_API_KEY=xxx uv run uvicorn app.main:app --reload

UI

cd ui
uv sync
BACKEND_HOST=localhost BACKEND_PORT=8000 uv run streamlit run streamlit_app.py

---

✅ 8. Data Persistence

• All indexed embeddings are stored in ChromaDB

• Path: ./data

• Mounted inside backend container at /app/data

• Safe across restarts

---

✅ 9. Summary

This project demonstrates:

✅ A single-agent RAG pipeline
✅ Built with modern Python tools (LangChain, Groq, Chroma, FastAPI)
✅ Clean UI via Streamlit
✅ Packaged with uv + Docker Compose
✅ Ready for production-grade expansion

Use this template to build:

• Customer support bots

• Internal knowledge base assistants

• Document Q&A systems

• Policy & compliance assistants