pip install perplexityai numpy

export PERPLEXITY_API_KEY="your_api_key_here"

python document_qa.py

python document_qa.py --interactive

import base64
import sys
import numpy as np
from perplexity import Perplexity

client = Perplexity()

# --- Chunking ---

def chunk_text(text, chunk_size=300, overlap=50):
    """Split text into overlapping chunks by word count."""
    words = text.split()
    chunks, start = [], 0
    while start < len(words):
        chunks.append(" ".join(words[start : start + chunk_size]))
        start += chunk_size - overlap
    return chunks

# --- Embedding helpers ---

def decode_embedding(b64_string):
    """Decode a base64-encoded int8 embedding to float32."""
    return np.frombuffer(base64.b64decode(b64_string), dtype=np.int8).astype(np.float32)

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# --- Build index ---

def build_index(documents, chunk_size=300, overlap=50):
    """Chunk documents and generate contextualized embeddings."""
    all_doc_chunks, metadata = [], []
    for doc in documents:
        chunks = chunk_text(doc["content"], chunk_size, overlap)
        all_doc_chunks.append(chunks)
        metadata.append({"title": doc["title"], "chunks": chunks})

    print(f"Embedding {sum(len(c) for c in all_doc_chunks)} chunks...")
    response = client.contextualized_embeddings.create(
        input=all_doc_chunks,
        model="pplx-embed-context-v1-4b"
    )

    index = []
    for doc_obj in response.data:
        meta = metadata[doc_obj.index]
        for chunk_obj in doc_obj.data:
            index.append({
                "text": meta["chunks"][chunk_obj.index],
                "embedding": decode_embedding(chunk_obj.embedding),
                "doc_title": meta["title"],
            })
    print(f"Index built: {len(index)} chunks.")
    return index

# --- Retrieve ---

def retrieve(index, query_text, top_k=3):
    """Embed the query and return the top-k most similar chunks."""
    qr = client.contextualized_embeddings.create(
        input=[[query_text]], model="pplx-embed-context-v1-4b"
    )
    q_emb = decode_embedding(qr.data[0].data[0].embedding)
    scored = sorted(
        [{**item, "score": float(cosine_similarity(q_emb, item["embedding"]))} for item in index],
        key=lambda x: x["score"], reverse=True,
    )
    return scored[:top_k]

# --- Generate answer ---

def generate_answer(query_text, chunks):
    """Send retrieved context to the Agent API for answer generation."""
    context = "\n\n".join(
        f"[Source {i}: {c['doc_title']}]\n{c['text']}" for i, c in enumerate(chunks, 1)
    )
    response = client.responses.create(
        model="anthropic/claude-sonnet-4-6",
        input=[{
            "role": "user",
            "content": (
                f"Answer the following question based ONLY on the provided context. "
                f"If the context does not contain enough information, say so.\n\n"
                f"Context:\n{context}\n\nQuestion: {query_text}"
            ),
        }],
        instructions=(
            "You are a precise document Q&A assistant. Answer using only the "
            "provided context. Cite source numbers. Be concise."
        ),
        max_output_tokens=1024,
    )
    return response.output_text

# --- Full pipeline ---

def query(index, query_text, top_k=3):
    print(f"\nQuery: {query_text}")
    retrieved = retrieve(index, query_text, top_k)
    for r in retrieved:
        print(f"  [{r['doc_title']}] score={r['score']:.4f}: {r['text'][:70]}...")
    return generate_answer(query_text, retrieved)

# --- Sample documents ---

sample_documents = [
    {
        "title": "Introduction to Transformers",
        "content": (
            "The Transformer architecture was introduced in the paper Attention Is All "
            "You Need by Vaswani et al. in 2017. It replaced recurrent layers with "
            "self-attention mechanisms, enabling parallel processing of input sequences. "
            "The key innovation is multi-head attention, which allows the model to attend "
            "to information from different representation subspaces. Transformers consist "
            "of an encoder and decoder with stacked layers of multi-head attention and "
            "feed-forward sub-layers. The architecture has become the foundation for "
            "modern language models including BERT, GPT, and T5."
        ),
    },
    {
        "title": "Retrieval-Augmented Generation",
        "content": (
            "Retrieval-Augmented Generation (RAG) combines information retrieval with "
            "text generation. Instead of relying solely on knowledge stored in model "
            "parameters, RAG systems retrieve relevant documents from an external "
            "knowledge base and use them as context. This reduces hallucination because "
            "the model grounds its responses in retrieved evidence. A typical RAG "
            "pipeline has three stages: indexing, retrieval, and generation. During "
            "indexing, documents are chunked and embedded into a vector store. At query "
            "time, the question is embedded and compared against stored vectors. The "
            "most relevant chunks are prepended to the prompt for answer generation."
        ),
    },
]

if __name__ == "__main__":
    index = build_index(sample_documents)
    if "--interactive" in sys.argv:
        print("\nInteractive mode. Type 'quit' to exit.\n")
        while True:
            q = input("Question: ").strip()
            if q.lower() in ("quit", "exit", "q"):
                break
            if q:
                print(f"\nAnswer:\n{query(index, q)}\n")
    else:
        answer = query(index, "How does RAG reduce hallucination?")
        print(f"\nAnswer:\n{answer}")

Embedding 4 chunks across 2 documents...
Index built: 4 chunks.

Query: How does RAG reduce hallucination?
  [Retrieval-Augmented Generation] score=0.8432: Retrieval-Augmented Generation (RAG) combines information retrieval w...
  [Retrieval-Augmented Generation] score=0.7891: most relevant chunks are prepended to the prompt for answer generatio...
  [Introduction to Transformers] score=0.6104: The Transformer architecture was introduced in the paper Attention Is...

Answer:
RAG reduces hallucination by grounding the model's responses in retrieved evidence
rather than relying solely on knowledge stored in model parameters [Source 1]. The
most relevant document chunks are prepended to the prompt, so the language model bases
its answers on concrete textual evidence from the knowledge base [Source 2].