INDEXING (Offline)
Documents → Chunking → Embedding → Vector DB

QUERYING (Online)
Query → Embed → Search → Retrieved Docs
                              ↓
Response ← LLM ← Context + Query

from rank_bm25 import BM25Okapi

tokenized_docs = [doc.split() for doc in documents]
bm25 = BM25Okapi(tokenized_docs)
scores = bm25.get_scores(query.split())

from sentence_transformers import SentenceTransformer
import faiss

model = SentenceTransformer('all-MiniLM-L6-v2')
embeddings = model.encode(documents)

index = faiss.IndexFlatIP(embeddings.shape[1])
faiss.normalize_L2(embeddings)
index.add(embeddings)

# Query
query_emb = model.encode([query])
faiss.normalize_L2(query_emb)
distances, indices = index.search(query_emb, k=5)

def hybrid_retrieve(query, k=5, alpha=0.5):
    bm25_scores = normalize(bm25.get_scores(query.split()))
    dense_scores = normalize(index.search(embed(query), len(docs))[0])

    hybrid = alpha * bm25_scores + (1-alpha) * dense_scores
    return [docs[i] for i in np.argsort(hybrid)[::-1][:k]]

def fixed_chunk(text, size=500, overlap=50):
    chunks = []
    for i in range(0, len(text), size - overlap):
        chunks.append(text[i:i+size])
    return chunks

def semantic_chunk(text, model, threshold=0.5):
    sentences = sent_tokenize(text)
    chunks, current = [], []

    for sent in sentences:
        current.append(sent)
        if len(current) > 1:
            sim = similarity(current[-2], current[-1], model)
            if sim < threshold:
                chunks.append(" ".join(current[:-1]))
                current = [sent]

    if current:
        chunks.append(" ".join(current))
    return chunks

def expand_query(query, model):
    prompt = f"Generate 3 alternative phrasings:\n{query}"
    return [query] + model.generate(prompt).split("\n")

def hyde(query, model):
    prompt = f"Write a paragraph answering:\n{query}"
    return model.generate(prompt)  # Use this for retrieval

from sentence_transformers import CrossEncoder

reranker = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2')

def rerank(query, docs, k=5):
    pairs = [(query, doc) for doc in docs]
    scores = reranker.predict(pairs)
    return sorted(zip(docs, scores), key=lambda x: -x[1])[:k]

def rag_metrics(query, response, context, ground_truth):
    return {
        "retrieval_precision": precision(retrieved, relevant),
        "retrieval_recall": recall(retrieved, relevant),
        "answer_relevance": similarity(response, ground_truth),
        "faithfulness": check_hallucination(response, context),
    }