Give your AI agents managed hybrid search

Try it without an account

A public demo account, so the quickstart above runs before you decide anything.

export OPENSOLR_EMAIL=mcp@opensolr.com
export OPENSOLR_API_KEY=420b8b23e7b12dc8ab838932145a5065

The index mcp_demo_d1__dense is already loaded with 300 news articles, so search, filtering and grounded answers work the moment you connect. You also get the write path: create your own index on the account, ingest into it and query it. Deletion is not available on this shared key — no index here can be deleted or reconfigured by hand. Whatever you create is removed automatically after 3 days.

• Anything you create there is deleted after 3 days. Automatically, without warning or export — indexes you created included.
• The account is shared with everyone reading this page. Your index is visible to them and they can add documents to it, as you can to theirs. Nobody can delete or reconfigure an index here — that is switched off for this key — but never put anything real, private or client-owned in it.
• The limits are per index, and deliberately small. 200 MB of bandwidth and 50 MB of disk per index. Bandwidth is the one you will hit first: it covers a demo, a tutorial and a proof of concept, and it will not carry an application.

When you want an index that is private, yours and still there next week, get your own key — the free plan is free forever, no card — and change the two variables above. Nothing else in your code changes.

16 tools your agent gets

Plain text in, ranked results out — the agent never touches a vector.

Local files and folders, PDFs page by page

Point the agent at a folder and it is searchable. Each file is read on Opensolr’s servers — its text, the text in its pictures (OCR, more than 100 languages), a short description of the pictures without text — and a PDF becomes one document per page, so a search lands on the page that answers it instead of a 200-page file that mentions it somewhere. Word, RTF, OpenDocument, text, HTML and scanned pictures are one document each.

# A file or a whole folder from the machine the agent runs on:
opensolr_index_files(
  index="contracts__dense",
  path="~/Documents/contracts",
  pattern="*.pdf",              # every file when left out
  metadata={"team": "legal"},
)
# -> {"documents": [...], "pending": [], "failed": [], "jobs": [...]}

# Or just read them, nothing indexed:
opensolr_extract_text(index="contracts__dense", path="~/Downloads/scan-0412.pdf")
# -> {"files": [{path, state, mime, "pages": [{page, text, is_ocr, lang}]}]}

The bytes travel once: a file the account already sent is not uploaded again, and sending the same files again replaces their documents. Pictures read by OCR count 0.5 of an AI request each; a file read before is free. Big files are read in the background: whatever is still being read comes back as pending — run again to finish them.

Index requirements, checked for you

Data Ingestion, vector and hybrid search and PDF pages need an index in a vector region that runs the Opensolr vector schema. Every index the package creates has it. On any other index the package checks once, with one request — never on every search — and tells you exactly what the index cannot do and how to fix it.

# What the index can do, and why not:
opensolr_check_schema(index="my_index")
# -> {"ready": false,
#     "capabilities": {"ingestion": true, "vector_search": false, "pdf_pages": true, "keyword_search": true},
#     "problems": ["... 1 differ: knn_vector (vectorDimension 768, expected 1024)."],
#     "fix": {"action": "apply_schema", "text": "apply_schema installs the Opensolr vector schema ..."}}

# Install the Opensolr vector schema (force=true when the index already holds documents):
opensolr_apply_schema(index="my_index")

• Only what cannot work is stopped. Data Ingestion on an index outside the vector regions, and vector or hybrid search on an index without the vector field, are refused with the exact reason before anything is uploaded or embedded. Keyword search runs on any index that has title, description and text fields.
• opensolr_check_schema answers whether the index is ready, what it can do (ingestion, vector search, PDF pages, keyword search), what differs from the Opensolr vector schema, and the fix.
• opensolr_apply_schema installs the Opensolr vector schema, the configuration every Opensolr vector index runs, so everything above works on the index. It replaces the index configuration: on an index that already holds documents it needs force=true, and those documents must be sent again.
• An index outside the vector regions cannot take it. Create a new index (opensolr_create_index) in one of the regions of opensolr_vector_regions and send your documents there.

Tested on our own production index

Every release runs a live end-to-end suite against real Opensolr infrastructure — no mocks.

• Full write path through the async Data Ingestion queue: queued → server-side embeddings & enrichment → searchable, with metadata and id round-trips verified. Metadata lands in typed Solr fields; the suffixes and what they enable are in the Site Search Schema Reference.
• Real-corpus retrieval against a replica of opensolr.com's own search index: pure-semantic hits with zero keyword overlap („how do I get my data back after a disaster” → backup docs), cross-lingual queries (non-English → English content), all hybrid modes and the full alpha range.
• PDF ingestion via rtf:true: server-side text extraction and content-type detection, then semantic retrieval from the extracted content.
• Grounded RAG answers: one call runs hybrid retrieval and feeds the top hits to the LLM (configurable docs/words, custom instruction) — verified with a question answerable only from the ingested PDF.
• Every tool exercised live: search modes (hybrid / semantic / lexical), ingestion with wait, job status, deletes by id and query, grounded RAG answers.