185 lines
4.6 KiB
Markdown
185 lines
4.6 KiB
Markdown
---
|
||
title: "AI Learning Series — Part 4:Embeddings, ChromaDB, Chunking & Retrieval (With a PDF → Chroma →…"
|
||
source: "https://medium.com/@vasanthancomrads/ai-learning-series-part-4-embeddings-chromadb-chunking-retrieval-with-a-pdf-chroma-abc5a98ecb5f"
|
||
author:
|
||
- "[[Vasanthan K]]"
|
||
published: 2025-11-24
|
||
created: 2026-04-06
|
||
description: "Master RAG essentials with embeddings, ChromaDB, and retrieval techniques. Follow a beginner-friendly walkthrough to build a PDF-to-Chroma RAG app."
|
||
tags:
|
||
- "clippings"
|
||
---
|
||
Retrieval-Augmented Generation (RAG) is one of the most practical AI patterns used today. Whether you’re building chatbots, internal knowledge assistants, or customer-facing AI apps, **you need to understand embeddings, chunking, vector databases and retrieval**.
|
||
|
||
In this blog, we’ll cover the core concepts step-by-step:
|
||
|
||
- Embeddings
|
||
- ChromaDB setup
|
||
- Chunking strategy (50–200 tokens)
|
||
- Retrieval pipeline
|
||
- **Exercise**: Build a complete **PDF → Chroma → Answer** RAG app in Python
|
||
|
||
### 🔍 1. What Are Embeddings?
|
||
|
||
Embeddings are **numerical representations of text**.
|
||
They convert sentences into high-dimensional vectors (arrays of floats) that capture meaning.
|
||
|
||
Example:
|
||
|
||
```c
|
||
"Apple the fruit" → [0.12, -0.93, 0.04, … ]
|
||
"Apple the company" → [1.02, 0.55, -0.31, … ]
|
||
```
|
||
|
||
Similar meanings → similar vectors.
|
||
Different meanings → distant vectors.
|
||
|
||
This is the foundation of **semantic search** and **RAG**.
|
||
|
||
### ⚙️ Generating Embeddings (Python Example)
|
||
|
||
```c
|
||
from openai import OpenAI
|
||
client = OpenAI()
|
||
|
||
text = "AI helps developers build faster."
|
||
emb = client.embeddings.create(
|
||
model="text-embedding-3-small",
|
||
input=text
|
||
)
|
||
print(len(emb.data[0].embedding)) # Dimensionality
|
||
```
|
||
|
||
### 🗂️ 2. ChromaDB Setup
|
||
|
||
[ChromaDB](https://www.trychroma.com/) is a lightweight vector database ideal for RAG apps.
|
||
|
||
### Install
|
||
|
||
```c
|
||
pip install chromadb pypdf openai
|
||
```
|
||
|
||
### Initialize a collection
|
||
|
||
```c
|
||
import chromadb
|
||
client = chromadb.Client()
|
||
|
||
collection = client.create_collection(
|
||
name="docs",
|
||
metadata={"hnsw:space": "cosine"} # cosine similarity
|
||
)
|
||
```
|
||
|
||
### ✂️ 3. Chunking Strategy (50–200 Tokens)
|
||
|
||
Large documents need to be **chunked** before embedding.
|
||
|
||
Why chunk?
|
||
|
||
- Embedding long text → loses precision
|
||
- Smaller chunks → better retrieval
|
||
- Great trade-off size: **50–200 tokens**
|
||
|
||
### Simple chunking example
|
||
|
||
```c
|
||
def chunk_text(text, chunk_size=150):
|
||
words = text.split()
|
||
for i in range(0, len(words), chunk_size):
|
||
yield " ".join(words[i:i + chunk_size])
|
||
```
|
||
|
||
## 🔄 4. Retrieval Pipeline
|
||
|
||
Here’s the basic RAG flow:
|
||
|
||

|
||
|
||
### 🧪 Exercise: Build a “PDF → Chroma → Answer” RAG App
|
||
|
||
Let’s build a **fully working** pipeline.
|
||
|
||
### Step 1: Load and Chunk the PDF
|
||
|
||
```c
|
||
from pypdf import PdfReader
|
||
|
||
def load_pdf(path):
|
||
reader = PdfReader(path)
|
||
text = ""
|
||
for page in reader.pages:
|
||
text += page.extract_text() + "\n"
|
||
return text
|
||
pdf_text = load_pdf("sample.pdf")
|
||
chunks = list(chunk_text(pdf_text, chunk_size=120))
|
||
print("Total chunks:", len(chunks))
|
||
```
|
||
|
||
### Step 2: Embed and Insert into Chroma
|
||
|
||
```c
|
||
from openai import OpenAI
|
||
client = OpenAI()
|
||
|
||
embeddings = client.embeddings.create(
|
||
model="text-embedding-3-small",
|
||
input=chunks
|
||
)
|
||
vectors = [e.embedding for e in embeddings.data]
|
||
collection.add(
|
||
documents=chunks,
|
||
embeddings=vectors,
|
||
ids=[f"id_{i}" for i in range(len(chunks))]
|
||
)
|
||
```
|
||
|
||
### Step 3: Retrieval Function
|
||
|
||
```c
|
||
def retrieve(query, top_k=3):
|
||
q_emb = client.embeddings.create(
|
||
model="text-embedding-3-small",
|
||
input=query
|
||
).data[0].embedding
|
||
|
||
results = collection.query(
|
||
query_embeddings=[q_emb],
|
||
n_results=top_k
|
||
)
|
||
return results["documents"][0]
|
||
```
|
||
|
||
### Step 4: Generate Final Answer Using Retrieved Context
|
||
|
||
```c
|
||
def answer(query):
|
||
context_chunks = retrieve(query)
|
||
context = "\n".join(context_chunks)
|
||
|
||
response = client.chat.completions.create(
|
||
model="gpt-4.1-mini",
|
||
messages=[
|
||
{"role": "system", "content": "You are a helpful assistant for answering based on context."},
|
||
{"role": "user", "content": f"Context:\n{context}\n\nQuestion:\n{query}"}
|
||
]
|
||
)
|
||
return response.choices[0].message["content"]
|
||
print(answer("What is the main idea of the document?"))
|
||
```
|
||
|
||
### 🎉 Final Output: A Working RAG App
|
||
|
||
You now have a complete:
|
||
|
||
**PDF → Chunk → Embed → ChromaDB → Retrieve → Answer**
|
||
|
||
pipeline.
|
||
|
||
This architecture is the foundation for:
|
||
|
||
- chat-with-PDF apps
|
||
- enterprise knowledge bots
|
||
- Q&A search tools
|
||
- internal documentation assistants |