LlamaIndex retrieval on managed Apache Solr
OpensolrVectorStore + OpensolrEmbedding: server-side GPU embeddings, native hybrid query mode, and standard metadata filters — no local model, no vector database to run.
Quickstart
Standard LlamaIndex interfaces — swap in Opensolr and your index, retriever, and query engine work unchanged.
from llama_index.core import VectorStoreIndex, StorageContext, Document from llama_index.vector_stores.opensolr import OpensolrVectorStore from llama_index.embeddings.opensolr import OpensolrEmbedding store = OpensolrVectorStore(index_name="mysite__dense", email="you@example.com", api_key="...", create_if_missing=True) embed_model = OpensolrEmbedding(email="you@example.com", api_key="...", index_name="mysite__dense") index = VectorStoreIndex.from_documents( [Document(text="Hybrid search fuses BM25 with vector similarity")], storage_context=StorageContext.from_defaults(vector_store=store), embed_model=embed_model, ) retriever = index.as_retriever(similarity_top_k=5)
What you get
The pieces most vector stores in the directory make you assemble yourself.
Server-side embeddings
1024-dim multilingual E5, computed on Opensolr's GPU infrastructure at both index and query time. No OpenAI key, no sentence-transformers install.
True HYBRID query mode
VectorStoreQueryMode.HYBRID with tunable alpha fuses BM25 and kNN scores per document via Opensolr's native {!hybrid} Solr parser — not client-side score juggling.
Standard filters, real Solr
MetadataFilters (EQ, NE, IN, NIN, ranges) map to Solr fq. And every index is plain Apache Solr underneath — facets, highlighting, the whole /select API.
Also available for: LangChain · MCP / AI Agents · Haystack · Laravel
Build your RAG pipeline on managed Solr
Free 15-day trial, no credit card — the included AI quota covers the whole quickstart.