Opensolr Changelog

Recent updates and improvements to the Opensolr platform.

Aug 2026 ×

Website Aug 25, 2026

  • New RAG in 60 seconds — a live sandbox, no signup required. The new Try it live page creates a real Apache Solr index for you in one click, lets you push your own JSON or a document URL, and then search it with hybrid search and ask questions answered by an LLM from your own content, with sources cited. You also get the raw Solr index credentials, so you can browse the documents and see the vector embeddings for yourself. Sandbox indexes delete themselves after 24 hours.

Security Aug 25, 2026

  • New Scoped API keys — stop sharing your master key. You can now create additional API keys from Account › API Keys, each restricted to exactly the endpoints you tick and, optionally, to a chosen subset of your indexes. Give a developer search-only access to one index, give your CI pipeline Data Ingestion rights and nothing else, or hand a contractor a key that expires on a date you choose. Keys can be revoked or regenerated instantly, and your master key — which is root-level and doubles as the initial index password — never has to leave your hands. Details in the Security & Trust Center.

Drupal Module Aug 18, 2026

  • Improved Search API opensolr 2.4.0 — new guided setup page. The Search API opensolr module's "Get started" tab is now a four-step guide that ticks off what you have already done: create your Opensolr account (15-day free trial), paste your email and API key, let Autoconfigure create the index and Search API server, then add your Search API index as usual. The old in-Drupal registration wizard, which relied on a retired API, is gone.
  • Improved Search API opensolr 2.3.0 — we now maintain the Search API connector. The Search API opensolr module (the drop-in Search API Solr connector for Opensolr) is now maintained by the Opensolr team. 2.3.0 fixes the admin fatal error that could appear when the Opensolr API was unreachable or an API key had been changed, makes the Key module integration an explicit opt-in (installing Key for something else no longer breaks your credentials), and is ready for Drupal 12. Drop-in update: run database updates after upgrading.

Search Aug 15, 2026

  • Improved AI answers now answer your question — not just summarize. When you ask a question on your hosted search page, the AI insight now formulates a direct, structured answer grounded strictly in your indexed content, with bold section headers — instead of a generic summary. The same grounded answer mode powers ai_answer in all AI integrations, with configurable retrieval depth (how many documents and how much text feed the answer) and an optional custom instruction (answer language, citation style, extraction tasks).

API Aug 15, 2026

  • Improved embed_and_search now matches your hosted search page exactly. The one-shot hybrid search endpoint runs the platform’s full tuned pipeline: your index’s saved Search Tuning applies automatically, natural-language questions are processed the same way as on your search page (stopwords cleaned for keyword matching, while the full phrase goes to the semantic embedder), and every tuning knob (fw_*, mm, search_mode, vector_topk, quality_boost, and more) accepts per-request overrides. Results returned via the API are now identical to your search page. Full parameter reference in the AI-Hints API guide.
  • Improved Your Search Tuning now applies everywhere — including all AI integrations. Everything you configure in Index Settings → Search Tuning (semantic↔lexical balance, field weights, minimum match, search mode, vector candidate pool, content quality boost) now applies automatically to every search and every RAG answer made through the LangChain, LlamaIndex, Haystack, Laravel Scout, and MCP integrations — the same tuned pipeline as your hosted search page. Each knob can also be overridden per call from code via the new tuning parameter. Packages updated: LangChain, LlamaIndex, Haystack (v0.2.5), Laravel Scout (v0.2.5), MCP (v0.2.6).

API Aug 14, 2026

  • New Grounded RAG answers in every AI integration. LangChain, MCP, LlamaIndex, Haystack, and Laravel Scout now include a one-call ai_answer: hybrid (BM25 + kNN) retrieval picks your top documents, and their content becomes the LLM context — the same pipeline that powers the AI answers on Opensolr hosted search pages. Configurable: how many documents and how many words feed the LLM, plus an optional custom instruction (answer language, citation style, extraction tasks). The AI-Hints API guide now documents this two-step retrieve-then-summarize pattern with full cURL, PHP, and Python examples.
  • Improved All AI integrations upgraded to v0.2.0. Writes in every integration — LangChain, MCP, LlamaIndex, Haystack, Laravel Scout — now go through the Data Ingestion API: documents are queued and enriched server-side (embeddings, sentiment, language, and all derived fields — identical to the Web Crawler), with progress visible in your Control Panel. Every integration also gains a lexical-only mode: pure keyword search with zero AI quota that works on any Opensolr index, including non-vector ones. Plus delete-by-query support and server-side PDF/DOCX text extraction via rtf:true.

Website Aug 14, 2026

API Aug 14, 2026

  • New Laravel Scout driver released. Add semantic + keyword search to any Laravel app: composer require opensolr/laravel-scout-opensolr, set SCOUT_DRIVER=opensolr, and Model::search() runs hybrid BM25 + kNN on a managed Solr index — with embeddings computed server-side. One index serves all your models. See the source on GitHub.
  • New Haystack integration released. Opensolr now plugs into Haystack pipelines as a DocumentStore with a hybrid retriever: pip install opensolr-haystack. No embedder components needed — documents and queries are embedded server-side on our GPU infrastructure, and retrieval fuses BM25 + kNN scores natively. See the PyPI package and the source on GitHub.
  • New LlamaIndex integration released. Opensolr is now a native LlamaIndex vector store: pip install llama-index-opensolr gives you OpensolrVectorStore and OpensolrEmbedding — server-side GPU embeddings, hybrid BM25 + kNN query mode, and standard metadata filters, on a managed Solr 9 index. See the PyPI package and the source on GitHub.
  • New Opensolr is now in the official MCP Registry. Any AI agent that speaks the Model Context Protocol — Claude Desktop, Claude Code, Cursor, Windsurf and more — can now use your Opensolr indexes as native tools: hybrid BM25 + kNN search, document indexing with server-side embeddings, and grounded RAG answers. One config entry with uvx opensolr-mcp and your API key. See the registry listing, the PyPI package, and the source on GitHub.
  • New New API endpoint: vector_regions. Returns the live list of vector-enabled environments (Solr 9.x with dense-vector schema and the hybrid query parser) — currently Chicago, Germany, and Finland. Tools like the LangChain package use it to discover valid locations automatically, so new regions work without any client updates. Need a dedicated vector-enabled environment in another region? We deploy them on request.
  • New Opensolr is now a native LangChain vector store. Install with pip install langchain-opensolr and every LangChain chain, agent, and RAG tutorial runs on a managed Solr 9 index — with embeddings computed server-side on our GPU infrastructure (multilingual, 1024 dimensions) and true hybrid BM25 + kNN search with a tunable semantic-lexical balance. No embedding model to configure, no third-party API keys. See the LangChain integration page, the PyPI package, and the source on GitHub.

WordPress Plugin Aug 13, 2026

  • Improved Verified against WordPress 7.1. Opensolr Search is tested and marked compatible with WordPress 7.1 (due 19 August 2026), including the iframed block editor and the new client-side media processing. No action needed on your side.
  • Fix Search result pagination and shortcode styling fixed. Paging through results no longer stops working on the search page, and the [opensolr_search] shortcode now loads its styles and scripts wherever you place it instead of rendering unstyled. The search page is also kept out of your sitemap and indexing, so it can no longer show up as a result inside its own result list.
  • Improved The WordPress search page now lives inside your own theme. Opensolr Search 1.0.25 turns /opensolr-search/ into an ordinary WordPress page, so your site header, navigation and footer wrap the search results exactly like every other page — no more standalone, theme-less screen. Because it is a real page, you can rename it, change its URL, add it to your menus or drop the [opensolr_search] shortcode on any other page; the search form, facets, sorting and pagination all follow wherever you put it. The page title above the search box is gone and the spacing is tightened, so results start right under your header. Grab it from WordPress.org or the plugin updates screen.

Security Aug 13, 2026

  • Improved Service availability by country. For security and compliance reasons, Opensolr accounts can no longer be created from, and payment methods can no longer be added from, the following countries: Albania, Bangladesh, Belarus, Bulgaria, Cambodia, Hong Kong, Indonesia, Iran, Iraq, Israel, Japan, Kuwait, Liechtenstein, Moldova, Pakistan, Romania, Russia, Singapore, Switzerland, Syria, Turkey, Ukraine, and Vietnam. Existing accounts are not affected. If you are based in one of these countries and you need an Opensolr index, this is not a final no — please reach out to us directly through our contact page and we will review your case individually and set your account up by hand.