Vektori

import asyncio
from vektori import Vektori

async def main():
    v = Vektori(
        embedding_model="openai:text-embedding-3-small",
        extraction_model="openai:gpt-4o-mini",
    )

    await v.add(
        messages=[
            {"role": "user", "content": "I only use WhatsApp, please don't email me."},
            {"role": "assistant", "content": "Got it, WhatsApp only."},
            {"role": "user", "content": "My outstanding amount is ₹45,000 and I can pay by Friday."},
        ],
        session_id="call-001",
        user_id="user-123",
    )

    results = await v.search(
        query="How does this user prefer to communicate?",
        user_id="user-123",
        depth="l1",  # facts + episodes
    )

    for fact in results["facts"]:
        print(f"[{fact['score']:.2f}] {fact['text']}")
    for episode in results["episodes"]:
        print(f"episode: {episode['text']}")

    await v.close()

asyncio.run(main())

# Just the facts
results = await v.search(query, user_id, depth="l0")

# Facts + episodes (recommended)
results = await v.search(query, user_id, depth="l1")

# Everything, with surrounding conversation context
results = await v.search(query, user_id, depth="l2", context_window=3)

import asyncio
from openai import AsyncOpenAI
from vektori import Vektori

client = AsyncOpenAI()

async def chat(user_id: str):
    v = Vektori(
        embedding_model="openai:text-embedding-3-small",
        extraction_model="openai:gpt-4o-mini",
    )
    session_id = f"session-{user_id}-001"
    history = []

    print("Chat with memory (type 'quit' to exit)\n")
    while True:
        user_input = input("You: ").strip()
        if user_input.lower() == "quit":
            break

        # 1. Pull relevant memory
        mem = await v.search(query=user_input, user_id=user_id, depth="l1")
        facts = "\n".join(f"- {f['text']}" for f in mem.get("facts", []))
        episodes = "\n".join(f"- {ep['text']}" for ep in mem.get("episodes", []))

        # 2. Inject into system prompt
        system = "You are a helpful assistant with memory.\n"
        if facts:    system += f"\nKnown facts:\n{facts}"
        if episodes: system += f"\nBehavioral episodes:\n{episodes}"

        # 3. Get response
        history.append({"role": "user", "content": user_input})
        resp = await client.chat.completions.create(
            model="gpt-4o-mini",
            messages=[{"role": "system", "content": system}, *history],
        )
        reply = resp.choices[0].message.content
        history.append({"role": "assistant", "content": reply})
        print(f"Assistant: {reply}\n")

        # 4. Store exchange
        await v.add(
            messages=[{"role": "user", "content": user_input},
                      {"role": "assistant", "content": reply}],
            session_id=session_id,
            user_id=user_id,
        )

    await v.close()

asyncio.run(chat("demo-user"))

# SQLite (default) — zero config, starts instantly
v = Vektori()

# PostgreSQL + pgvector — production scale
v = Vektori(database_url="postgresql://localhost:5432/vektori")

# Neo4j — native graph traversal for Episode layer
v = Vektori(
    storage_backend="neo4j",
    database_url="bolt://localhost:7687",
    embedding_dimension=1024,   # must match your embedding model
)

# Qdrant — dedicated vector DB, cloud-ready
v = Vektori(
    storage_backend="qdrant",
    database_url="http://localhost:6333",
    embedding_dimension=1024,
)

# Qdrant Cloud
v = Vektori(
    storage_backend="qdrant",
    database_url="https://your-cluster.qdrant.io",
    qdrant_api_key="your-api-key",
    embedding_dimension=1024,
)

# Milvus — high-scale vector store with partition-key isolation
v = Vektori(
    storage_backend="milvus",
    database_url="http://localhost:19530",
    embedding_dimension=1024,
)

# Milvus / Zilliz Cloud
v = Vektori(
    storage_backend="milvus",
    database_url="https://your-cluster-endpoint",
    milvus_token="your-api-key-or-token",
    embedding_dimension=1024,
)

# In-memory — tests / CI
v = Vektori(storage_backend="memory")

# OpenAI
v = Vektori(
    embedding_model="openai:text-embedding-3-small",
    extraction_model="openai:gpt-4o-mini",
)

# Azure OpenAI
# Ensure AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_API_KEY are set
# Note: The string after "azure:" must match your specific Azure deployment names
v = Vektori(
    embedding_model="azure:my-embedding-deployment",
    extraction_model="azure:my-gpt-4o-deployment",
)

# GitHub Models (Copilot)
# Requires GITHUB_TOKEN. You can get one by running `./scripts/get_github_token.sh`
v = Vektori(
    embedding_model="github:text-embedding-3-small",
    extraction_model="github:gpt-4o",
)

# Anthropic
v = Vektori(
    embedding_model="anthropic:voyage-3",
    extraction_model="anthropic:claude-haiku-4-5-20251001",
)

# Fully local, no API keys, no internet
v = Vektori(
    embedding_model="ollama:nomic-embed-text",
    extraction_model="ollama:llama3",
)

# Sentence Transformers (local, no Ollama required)
v = Vektori(embedding_model="sentence-transformers:all-MiniLM-L6-v2")

# BGE-M3 — multilingual, 1024-dim, best local embeddings we've found
v = Vektori(embedding_model="bge:BAAI/bge-m3")

# LiteLLM — 100+ providers through one interface
v = Vektori(extraction_model="litellm:groq/llama3-8b-8192")

# NVIDIA embedding models (Matryoshka: 384-2048 dimensions)
v = Vektori(
    embedding_model="nvidia:llama-nemotron-embed-1b-v2",
    embedding_dimension=1024,  # Optional: 384, 512, 768, 1024, or 2048
)

# NVIDIA LLM models (nvidia/ prefix auto-added)
v = Vektori(extraction_model="nvidia:llama-3.3-nemotron-super-49b-v1")

# Third-party models hosted on NVIDIA NIM (use full path)
v = Vektori(extraction_model="nvidia:z-ai/glm5")