Vector databases

Supported backends

Agent RT includes dependency-light HTTP adapters for Chroma, Milvus, Pinecone, Qdrant, and Weaviate. FAISS and pgvector remain registry extensions because their normal integration paths require native/local or database drivers.

Configure once

The common environment variables are the same for every backend:

export AGENT_RT_VECTOR_DB="qdrant"
export AGENT_RT_VECTOR_DB_URL="https://your-vector-db.example"
export AGENT_RT_VECTOR_DB_COLLECTION="docs"

# Optional generic credential and timeout.
export AGENT_RT_VECTOR_DB_API_KEY="..."
export AGENT_RT_VECTOR_DB_TIMEOUT_SECONDS="20"

You may use the backend-native credential variable instead of AGENT_RT_VECTOR_DB_API_KEY. Backend-specific settings use the AGENT_RT_VECTOR_DB_OPTION_* prefix.

Switch backends without changing code

The application registers the popular backends once. Selection happens later from the environment.

# Qdrant
export AGENT_RT_VECTOR_DB="qdrant"
export AGENT_RT_VECTOR_DB_URL="https://qdrant.example"
export AGENT_RT_VECTOR_DB_COLLECTION="docs"
export QDRANT_API_KEY="..."

# Switch the same code to Pinecone
export AGENT_RT_VECTOR_DB="pinecone"
export AGENT_RT_VECTOR_DB_URL="https://your-index.svc.pinecone.io"
export AGENT_RT_VECTOR_DB_COLLECTION="docs"
export PINECONE_API_KEY="..."
export AGENT_RT_VECTOR_DB_OPTION_NAMESPACE="production"

Python

from agent_rt import (
    RetrievalQuery,
    VectorDBProviderRegistry,
    load_model,
    register_popular_vector_db_backends,
    vector_db_provider_from_environment,
)

embedding_provider = load_model()

registry = VectorDBProviderRegistry()
register_popular_vector_db_backends(
    registry,
    embedding_provider=embedding_provider,
)

provider = vector_db_provider_from_environment(registry)
results = await provider.search(
    RetrievalQuery("How does Agent RT handle tools?", limit=5)
)

TypeScript

const {
  VectorDBProviderRegistry,
  loadModel,
  registerPopularVectorDBBackends,
  vectorDBProviderFromEnvironment,
} = require("agent-rt");

const embeddingProvider = await loadModel();

const registry = new VectorDBProviderRegistry();
registerPopularVectorDBBackends(registry, { embeddingProvider });

const provider = vectorDBProviderFromEnvironment(registry);
const results = await provider.search({
  text: "How does Agent RT handle tools?",
  limit: 5,
});

LangChain vector-store compatibility

Existing LangChain retrieval code can keep the vendor-shaped class names while moving the import to Agent RT. The adapter fixes the backend implied by the import and sends similarity search through Agent RT's vector DB provider.

from agent_rt.langchain_qdrant import QdrantVectorStore

store = QdrantVectorStore(
    embedding=embeddings,
)

documents = await store.asimilarity_search(
    "How does Agent RT retrieve context?",
    k=4,
)

TypeScript/JavaScript exports the same compatibility layer through agent-rt/@langchain/chroma, agent-rt/@langchain/pinecone, agent-rt/@langchain/qdrant, agent-rt/@langchain/milvus, and agent-rt/@langchain/weaviate. Community-style subpaths such as agent-rt/@langchain/community/vectorstores/qdrant are also published.

import { QdrantVectorStore } from "agent-rt/@langchain/qdrant";

const store = new QdrantVectorStore(embeddings);
const documents = await store.similaritySearch(
  "How does Agent RT retrieve context?",
  4,
);

LlamaIndex vector-store compatibility

LlamaIndex migrations preserve the upstream vector_stores module hierarchy in Python and expose equivalent package aliases in TypeScript.

from agent_rt.llama_index.vector_stores.qdrant import QdrantVectorStore
from agent_rt.llamaindex import VectorStoreIndex

vector_store = QdrantVectorStore()
index = VectorStoreIndex.from_vector_store(
    vector_store,
    embed_model=embed_model,
)
nodes = await index.as_retriever(
    similarity_top_k=4,
).aretrieve("How does Agent RT migrate vector retrieval?")

TypeScript/JavaScript equivalents are published at agent-rt/@llamaindex/chroma, agent-rt/@llamaindex/pinecone, agent-rt/@llamaindex/qdrant, agent-rt/@llamaindex/milvus, and agent-rt/@llamaindex/weaviate.

import {
  QdrantVectorStore,
  VectorStoreIndex,
} from "agent-rt/@llamaindex/qdrant";

const vectorStore = new QdrantVectorStore();
const index = VectorStoreIndex.fromVectorStore(vectorStore, {
  embedModel,
});
const nodes = await index.asRetriever({
  similarityTopK: 4,
}).retrieve("How does Agent RT migrate vector retrieval?");

Embedding queries

Vector databases search numeric embeddings while Agent RT retrieval queries are text-first. Supply an EmbeddingModelProvider when registering the built-in backends. OpenAI and OpenAI-compatible Agent RT providers support embeddings. If your application already creates embeddings elsewhere, pass a numeric filters.vector instead.

await provider.search(
    RetrievalQuery(
        "precomputed query",
        filters={"vector": [0.12, -0.03, 0.44]},
    )
)

await provider.search({
  text: "precomputed query",
  filters: { vector: [0.12, -0.03, 0.44] },
});

Backend options

Runnable examples

See python/examples/07_vector_db.py and typescript/examples/07_vector_db.js in the repository. Both examples use the same environment-driven backend selection shown above.