from langchain.text_splitter import RecursiveCharacterTextSplitter

# Evaluate chunk_size on your domain data — never use 512 blindly
splitter = RecursiveCharacterTextSplitter(
    chunk_size=800,
    chunk_overlap=100,
    separators=["\n\n", "\n", ". ", " "],
)

chunks = splitter.create_documents(
    texts=[doc.page_content for doc in raw_docs],
    metadatas=[{"source": doc.metadata["source"], "timestamp": doc.metadata.get("timestamp")} for doc in raw_docs],
)

from openai import OpenAI
import qdrant_client
from qdrant_client.models import VectorParams, Distance, PointStruct

client = OpenAI()
qdrant = qdrant_client.QdrantClient("localhost", port=6333)

# Create collection
qdrant.recreate_collection(
    collection_name="knowledge_base",
    vectors_config=VectorParams(size=1536, distance=Distance.COSINE),
)

def embed_chunks(chunks: list[str], model: str = "text-embedding-3-small") -> list[list[float]]:
    response = client.embeddings.create(input=chunks, model=model)
    return [r.embedding for r in response.data]

# Idempotent upsert with deduplication via deterministic IDs
import hashlib, uuid

points = []
for i, chunk in enumerate(chunks):
    doc_id = str(uuid.UUID(hashlib.md5(chunk.page_content.encode()).hexdigest()))
    embedding = embed_chunks([chunk.page_content])[0]
    points.append(PointStruct(id=doc_id, vector=embedding, payload=chunk.metadata))

qdrant.upsert(collection_name="knowledge_base", points=points)

from qdrant_client.models import Filter, FieldCondition, MatchValue, SparseVector
from rank_bm25 import BM25Okapi

def hybrid_search(query: str, tenant_id: str, top_k: int = 20) -> list:
    # Dense retrieval
    query_embedding = embed_chunks([query])[0]
    tenant_filter = Filter(must=[FieldCondition(key="tenant_id", match=MatchValue(value=tenant_id))])
    dense_results = qdrant.search(
        collection_name="knowledge_base",
        query_vector=query_embedding,
        query_filter=tenant_filter,
        limit=top_k,
    )

    # Sparse retrieval (BM25)
    corpus = [r.payload.get("text", "") for r in dense_results]
    bm25 = BM25Okapi([doc.split() for doc in corpus])
    bm25_scores = bm25.get_scores(query.split())

    # Reciprocal Rank Fusion
    ranked = sorted(
        zip(dense_results, bm25_scores),
        key=lambda x: 0.6 * x[0].score + 0.4 * x[1],
        reverse=True,
    )
    return [r for r, _ in ranked[:top_k]]

import cohere

co = cohere.Client("YOUR_API_KEY")

def rerank(query: str, results: list, top_n: int = 5) -> list:
    docs = [r.payload.get("text", "") for r in results]
    reranked = co.rerank(query=query, documents=docs, top_n=top_n, model="rerank-english-v3.0")
    return [results[r.index] for r in reranked.results]

# Run precision@k and recall@k against a labeled evaluation set
# python evaluate.py --metrics precision@10 recall@10 mrr --collection knowledge_base

from ragas import evaluate
from ragas.metrics import context_precision, context_recall, faithfulness, answer_relevancy
from datasets import Dataset

eval_dataset = Dataset.from_dict({
    "question": questions,
    "contexts": retrieved_contexts,
    "answer": generated_answers,
    "ground_truth": ground_truth_answers,
})

results = evaluate(eval_dataset, metrics=[context_precision, context_recall, faithfulness, answer_relevancy])
print(results)