How do you build a basic RAG (Retrieval-Augmented Generation) pipeline with ChromaDB?

RAG combines ChromaDB's semantic retrieval with an LLM's generation ability. The pipeline has two phases: indexing (chunk documents, embed, store in ChromaDB) and retrieval (embed the user query, fetch similar chunks, inject into LLM prompt).

import chromadb
from chromadb.utils import embedding_functions
from openai import OpenAI
import os

# --- INDEXING PHASE (run once) ---
chroma_client = chromadb.PersistentClient(path="./rag_db")
ef = embedding_functions.OpenAIEmbeddingFunction(
    api_key=os.environ["OPENAI_API_KEY"],
    model_name="text-embedding-3-small",
)
collection = chroma_client.get_or_create_collection(
    "company_docs", embedding_function=ef, metadata={"hnsw:space": "cosine"}
)

# Chunk and index your knowledge base
documents = [
    "ChromaDB supports cosine, l2, and inner-product distance metrics.",
    "Persistent storage in ChromaDB uses SQLite under the hood.",
    "The default embedding model is all-MiniLM-L6-v2 with 384 dimensions.",
    "ChromaDB collections support metadata filtering with $eq, $gt, $in operators.",
]
collection.add(
    documents=documents,
    ids=[f"doc-{i}" for i in range(len(documents))],
)

# --- RETRIEVAL + GENERATION PHASE (run per query) ---
def rag_answer(user_question: str, n_results: int = 3) -> str:
    # 1. Retrieve relevant chunks from ChromaDB
    results = collection.query(
        query_texts=[user_question],
        n_results=n_results,
        include=["documents", "distances"],
    )
    context_chunks = results["documents"][0]  # list of retrieved texts
    context = "\n\n".join(
        f"[{i+1}] {chunk}" for i, chunk in enumerate(context_chunks)
    )

    # 2. Build an augmented prompt
    prompt = f"""Answer the question using ONLY the context below.
    If the answer is not in the context, say "I don't know."

    Context:
    {context}

    Question: {user_question}
    Answer:"""

    # 3. Generate answer with LLM
    openai_client = OpenAI()
    response = openai_client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": prompt}],
    )
    return response.choices[0].message.content

print(rag_answer("What distance metrics does ChromaDB support?"))