from simplevecdb import VectorDB
from openai import OpenAI

db = VectorDB("knowledge.db")
collection = db.collection("docs")
client = OpenAI()

texts = ["Paris is the capital of France.", "Mitochondria powers cells."]
embeddings = [
    client.embeddings.create(model="text-embedding-3-small", input=t).data[0].embedding
    for t in texts
]

collection.add_texts(
    texts=texts,
    embeddings=embeddings,
    metadatas=[{"category": "geography"}, {"category": "biology"}]
)

# Search
query_emb = client.embeddings.create(
    model="text-embedding-3-small",
    input="capital of France"
).data[0].embedding

results = collection.similarity_search(query_emb, k=1)
print(results[0][0].page_content)  # "Paris is the capital of France."

# Filter by metadata
filtered = collection.similarity_search(query_emb, k=10, filter={"category": "geography"})

from simplevecdb import VectorDB
from simplevecdb.embeddings.models import embed_texts

db = VectorDB("local.db")
collection = db.collection("docs")

texts = ["Paris is the capital of France.", "Mitochondria powers cells."]
embeddings = embed_texts(texts)  # Local HuggingFace models

collection.add_texts(texts=texts, embeddings=embeddings)

# Search
query_emb = embed_texts(["capital of France"])[0]
results = collection.similarity_search(query_emb, k=1)

# Hybrid search (BM25 + vector)
hybrid = collection.hybrid_search("powerhouse cell", k=2)

from simplevecdb.integrations.langchain import SimpleVecDBVectorStore
from langchain_openai import OpenAIEmbeddings

store = SimpleVecDBVectorStore(
    db_path="langchain.db",
    embedding=OpenAIEmbeddings(model="text-embedding-3-small")
)

store.add_texts(["Paris is the capital of France."])
results = store.similarity_search("capital of France", k=1)
hybrid = store.hybrid_search("France capital", k=3)  # BM25 + vector

from simplevecdb.integrations.llamaindex import SimpleVecDBLlamaStore
from llama_index.embeddings.openai import OpenAIEmbedding

store = SimpleVecDBLlamaStore(
    db_path="llama.db",
    embedding=OpenAIEmbedding(model="text-embedding-3-small")
)

from simplevecdb import VectorDB, Quantization

db = VectorDB("app.db")
users = db.collection("users", quantization=Quantization.FLOAT16)  # 2x memory savings
products = db.collection("products", quantization=Quantization.BIT)  # 32x compression

# Isolated namespaces
users.add_texts(["Alice likes hiking"], embeddings=[[0.1]*384])
products.add_texts(["Hiking boots"], embeddings=[[0.9]*384])

# Vector similarity (cosine/L2) - adaptive search by default
results = collection.similarity_search(query_vector, k=10)

# Force exact search for perfect recall (brute-force)
results = collection.similarity_search(query_vector, k=10, exact=True)

# Force HNSW approximate search (faster, may miss some results)
results = collection.similarity_search(query_vector, k=10, exact=False)

# Parallel search with explicit thread count
results = collection.similarity_search(query_vector, k=10, threads=8)

# Batch search - 10x throughput for multiple queries
queries = [query1, query2, query3]  # List of embedding vectors
batch_results = collection.similarity_search_batch(queries, k=10)

# Keyword search (BM25)
results = collection.keyword_search("exact phrase", k=10)

# Hybrid (BM25 + vector fusion)
results = collection.hybrid_search("machine learning", k=10)
results = collection.hybrid_search("ML concepts", query_vector=my_vector, k=10)

# Metadata filtering
results = collection.similarity_search(
    query_vector,
    k=10,
    filter={"category": "technical", "verified": True}
)

from simplevecdb import VectorDB

# Create encrypted database
db = VectorDB("secure.db", encryption_key="your-secret-key")
collection = db.collection("confidential")

collection.add_texts(["sensitive data"], embeddings=[[0.1]*384])
db.close()

# Reopen requires same key
db = VectorDB("secure.db", encryption_key="your-secret-key")

def load_documents():
    for line in open("large_file.jsonl"):
        doc = json.loads(line)
        yield (doc["text"], doc.get("metadata"), doc.get("embedding"))

for progress in collection.add_texts_streaming(load_documents(), batch_size=1000):
    print(f"Processed {progress['docs_processed']} documents")

# Add parent document
parent_ids = collection.add_texts(["Main document"], embeddings=[[0.1]*384])

# Add children
child_ids = collection.add_texts(
    ["Chunk 1", "Chunk 2"],
    embeddings=[[0.11]*384, [0.12]*384],
    parent_ids=[parent_ids[0], parent_ids[0]]
)

# Navigate hierarchy
children = collection.get_children(parent_ids[0])
parent = collection.get_parent(child_ids[0])
descendants = collection.get_descendants(parent_ids[0])

# Cluster documents and auto-generate tags
result = collection.cluster(n_clusters=5)
tags = collection.auto_tag(result, method="tfidf")
collection.assign_cluster_metadata(result, tags)

# Save for fast assignment of new documents
collection.save_cluster("categories", result)
collection.assign_to_cluster("categories", new_doc_ids)

# Ensure all vectors in a collection have identical dimensions
collection = db.collection("docs", dim=384)  # Explicit dimension