Opensolr Changelog

Recent updates and improvements to the Opensolr platform.

API Aug 26, 2026

  • Improved All AI integrations updated. LangChain, LlamaIndex, Haystack, the MCP server and Laravel Scout all ship the new answer behaviour. Update with pip install -U or composer update.

WordPress Plugin Aug 26, 2026

  • Improved Opensolr Search 1.0.27 for WordPress. The same AI answer improvements: fuller, properly formatted answers, restricted to what your indexed content states. Update from Plugins → Updates in your WordPress admin.

Drupal Module Aug 26, 2026

  • Improved Opensolr Search 4.2.1 for Drupal. The same AI answer improvements: fuller, properly formatted answers, restricted to what your indexed content states. Drop-in upgrade, no database updates and no re-index.

Web Crawler Aug 26, 2026

  • Fix Product codes and identifiers are no longer altered before indexing. Underscores were being replaced with spaces across the whole text while converting emoji to words, so identifiers such as ABC_123_XL were indexed as ABC 123 XL. Emoji are still converted; everything else is now indexed exactly as written.

Search Aug 26, 2026

  • Fix Search queries keep their punctuation. Characters such as [ ] { } ( ) ^ ~ ! were being stripped from every query before it ran. They are now passed to Solr safely as a value rather than as query syntax, so a question reaches both the search engine and the AI assistant exactly as you typed it.

API Aug 26, 2026

  • Improved The ai_summary API is now fully deterministic: your instruction is the prompt. Whatever you send in instruction is exactly what the model reads, byte for byte. Nothing reorders it, relabels it, appends to it or shortens it, so a prompt you tuned behaves the same on every call. Retrieval stays yours: run embed_and_search, take your top results and place them in the prompt where you want them. The query and context parameters still work for existing integrations. Prompts up to 100,000 characters are accepted.

Search Aug 26, 2026

  • Improved AI answers are now as detailed as your content allows, and readable. Answers used to be squeezed into a short paragraph that dropped most of what the matched pages actually said. They now cover every relevant point, with the concrete details such as model numbers, measurements, standards and dates, formatted as short paragraphs and bullet lists instead of a wall of text. The assistant is also restricted to what your indexed content states, so it no longer pads an answer with plausible advice or product names that appear nowhere on your site.

WordPress Plugin Aug 25, 2026

  • Improved Opensolr Search 1.0.26 for WordPress. The same AI answer improvements as the platform: AI Hints answer your question directly instead of hedging, the Document Reader returns a full readable rendition of the page instead of a summary, and your question is no longer echoed above the answer. Update from Plugins → Updates in your WordPress admin.

API Aug 25, 2026

  • Improved Every AI integration ships the improved answer behaviour. LangChain, LlamaIndex, Haystack, the MCP server and Laravel Scout all now send a grounded answer instruction by default and drop weakly matching documents before generating, so RAG answers are direct and stay on topic. Update with pip install -U or composer update.

Drupal Module Aug 25, 2026

  • Improved Opensolr Search 4.2.0 for Drupal. AI Hints answer the question directly instead of describing the results, the Document Reader returns a full readable rendition instead of a summary, and the query is no longer echoed above the answer. Also includes Drupal 12 readiness work. Drop-in upgrade: no database updates, no configuration changes, no re-index.

Search Aug 25, 2026

  • Improved The Document Reader is now a readable rendition, not a summary. Reading a result inside search used to give you a condensed summary that always opened with the same two headings. It now renders the full source text in readable form and keeps the detail, so you can read the page without leaving the results and without opening the original.
  • Improved AI answers stopped hedging, and stopped repeating your question. Ask something your content actually covers and the answer now opens with the fact itself instead of a preamble about what the content does or does not address. Yes or no questions get a straight answer; every other question opens with the substance. The assistant no longer contradicts itself by dismissing your question and then answering it anyway, and it no longer echoes your query back as a heading above the answer. Weakly matching results are now dropped before the answer is generated, so a distant tail match can no longer pull the answer off topic. Live on your hosted search page, in the RAG sandbox and across the AI API.

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.

Drupal Module Jul 31, 2026

  • New Drupal module: point multiple Drupal sites at one shared search index. The Settings page now offers two options — create a fresh index in your chosen region, or attach the site to any existing index from your Opensolr account, with an optional data reset and one-click schema re-configuration. Perfect for multi-site setups where several Drupal instances feed a single search experience. Read the setup guide →

Server Management Jul 31, 2026

  • New Varnish full-page cache is now fully configurable from the control panel. The Varnish card in your server’s Services tab has a new Configure button: add cache-exclusion rules for stateful pages (shopping carts, product compare, anything per-visitor) with a built-in URL tester and one-click purge of matching pages — or edit the raw VCL directly. Every save is backed up, compile-tested and applied with zero downtime, so a typo can never take your site down or empty a warm cache. Setting up Varnish for the first time? The editor opens with a commented, production-tested starter template that walks you through the whole wiring. Read the Varnish docs.

Search Jul 24, 2026

  • New Hybrid search now runs on the Opensolr {!hybrid} parser. Every vector-enabled index now fuses keyword (BM25) and semantic (vector) relevance through {!hybrid} — a proprietary Opensolr Solr query parser that runs only on Opensolr clusters. You get correct score fusion, real search-mode semantics (Union / Keywords Required / Meaning Required / Intersection), and natural-language, cross-lingual queries that just work — plus semantic search over documents. Learn how it works →

Server Management Jul 22, 2026

  • New Live Varnish & Memcached stats in Server Management. Every running Varnish or Memcached service in your server’s Services tab now has a Stats button — one click opens a clear snapshot of how your cache is really performing: overall hit rate, requests served straight from cache versus fetched from the backend, objects stored, memory used, evictions and more. Hover any metric’s info icon for a plain-English explanation, and see exactly how long the counters have been running. Read more in the Server Management docs.

Security Jul 21, 2026

  • New New Security & Trust Center. Read how Opensolr protects your data — our security controls mapped to the SOC 2 Trust Services Criteria and ISO 27001, with a downloadable overview for your vendor security reviews. Visit the Trust Center.

Drupal Module Jun 29, 2026

  • Improved OpenSolr Turbo Indexer 2.5.2 — Drupal 11 / Drush 13 compatibility. The OpenSolr Turbo Indexer now starts reliably on the latest Drush 13, and its parallel background workers run under the correct PHP on every hosting setup. Faster, parallel Solr indexing — fully compatible with Drupal 11. Drop-in update, no configuration changes and no re-index required.

Security Jun 29, 2026

  • Improved Fleet-wide Solr security hardening. We have patched a potential security issue affecting older Apache Solr versions and strengthened server-side request controls across our entire Solr infrastructure. The update was rolled out to every server automatically — no customer action is required, and your indexes and data are unaffected.

Drupal Module Jun 18, 2026

  • Improved Drupal 12 support. The Opensolr Search Drupal module (3.9.0) is now compatible with Drupal 12, alongside Drupal 10.1 and 11. This is a drop-in upgrade: no configuration changes, no database updates, and no re-index required. Released on drupal.org.

Drupal Module Jun 5, 2026

  • Fix Fixed a bug in the Opensolr Search Drupal module (3.8.5) where viewing content that references a non-translatable entity could trigger a fatal error. Fixed and released on drupal.org.

Account Jun 2, 2026

  • New One-click unsubscribe from product & campaign emails. The Communications page now has a toggle for product updates, feature announcements, and marketing emails — flip it off to opt out without hunting for the unsubscribe link inside an email. Equivalent to clicking that link, but reachable from your admin panel any time you want to change it. Billing, critical service alerts, and invoice emails are unaffected (they stay always-on to protect your service).

Billing Jun 2, 2026

  • Improved Payment Profile VAT handling — multiple improvements. Real-time validation now shows status next to your VAT number as you type (verified, invalid, Romania, non-EU). VAT numbers entered with formatting (spaces, dots, dashes) or with the country prefix doubled (e.g. DE prefix + DEXXXXXX number) are auto-normalized before reaching Stripe. Tax IDs that already existed on your Stripe customer but weren't recorded on our side are now auto-detected and synced on next save in your Payment Profile — no more silent divergences between your account and Stripe. Changing the country also clears the VAT field so it can't drift into an invalid combination.

Drupal Module Jun 2, 2026

  • Fix Fixed a fatal error in the Opensolr Search Drupal module (3.8.4) during data ingestion when a content type has an entity_reference field pointing to a config entity (for example Domain from the Domain module). The ingestion job aborted with "Call to undefined method ::hasTranslation()" — config entities don't implement the translation interface, so the translation-resolution helper now short-circuits for them and ingestion runs end-to-end. Thanks to rickydev90 on drupal.org for the clean report and patch in #3593311.

Billing May 25, 2026

  • Fix Fixed VAT number validation for GB on the Opensolr ezcmd.com service. UK VAT lookups now return correct results.

Drupal Module Apr 24, 2026

  • Fix Saving a new Facet Mapping now takes effect immediately — no drush cr required. Render cache tags are invalidated on save so every cached node and commerce product page re-renders with the newly-mapped opensolr:* meta tags on next view.

WordPress Plugin Apr 24, 2026

  • Fix Facet Mapping saves persist correctly. A legacy sanitize callback in the WordPress plugin was silently stripping every saved row under the sanitize_option_opensolr_settings filter — saves looked successful but the data never made it to the database. Fixed: the callback now handles the new rich mapping shape AND auto-promotes any legacy rows on first save.

Facet Mapping Apr 24, 2026

  • Fix Image and File field mappings now emit a real URL instead of the bare attachment ID. Mapping a Drupal field_image or a WordPress meta that stores an attachment ID (ACF image field with Return Format = ID, _thumbnail_id, custom image_attachment_id) now resolves to a working public URL. Guarded against numeric SKU/price fields being silently rewritten.
  • Fix Multi-valued field mappings work correctly end-to-end. Drupal taxonomy terms, ACF Checkbox/Select-multiple/Relationship/Gallery arrays, and WooCommerce attributes (all stored differently — multi-row vs serialized-array) now all emit as one <meta property="opensolr:X_sm"> tag per value. The Web Crawler aggregates repeated tags into a Solr array, matching what real-time ingestion already writes — so crawler and ingestion produce identical documents.
  • New Every indexable WordPress source is now mappable — core post columns (post_title, post_content, post_excerpt, post_date, post_author, …), ALL postmeta keys (the underscore-prefixed WooCommerce core fields like _price, _sku, _stock, _thumbnail_id are now visible — previously hidden as "private"), every public taxonomy, all WooCommerce pa_* attribute taxonomies, plus synthetic featured_image_url and gallery_image_urls aggregates.
  • Improved Facet Mapping got a big UX upgrade on both platforms. Pick a Drupal/WordPress field and the Solr Type dropdown auto-fills with the detected suffix — _s for a plain string field, _sm for a multi-valued taxonomy, _f for a WooCommerce price, _dt for a date field. Every entry in the field dropdown shows its detected type inline (post_tag — multi, string; _price — single, float) so you know before you click.

Drupal Module Apr 24, 2026

  • New Opensolr Search Drupal module 3.8.0 tagged on drupal.org — first public release since 3.6.0. Configurable result thumbnail field, auto-suggesting Facet Mapping form, full multi-valued field pipeline (crawler + ingestion + meta tags).

WordPress Plugin Apr 24, 2026

  • New Opensolr Search WordPress plugin 1.0.19 is live on WordPress.org — admins will see the update prompt within 15 minutes of publication. Major Facet Mapping overhaul, plus every fix from the last two weeks rolled into one stable release.

Search Apr 22, 2026

  • Fix Fixed a JavaScript SecurityError thrown when the Opensolr search page is embedded inside a cross-origin iframe. Browsers block showPicker() calls from cross-origin frames; the call is now wrapped in a try/catch so the browser restriction is silently handled instead of surfacing as an uncaught exception that could disrupt other search functionality on the host page.
  • Fix Fixed four search parameter bugs across all platforms. (1) Wildcard searches (*:*) no longer send any highlighting parameters to Solr — highlighting on a catch-all query is meaningless and wastes server cycles. (2) The Solr highlight query (hl.q) was incorrectly set to *:* instead of the real search terms, so highlighted snippets never matched actual keywords. (3) A hardcoded stats=true / stats.field=price_f block was attached to every query even for non-commerce indexes. (4) currency_s was hardcoded into the facet field list regardless of whether the index has that field. All four are fixed in Opensolr, the Drupal module, and the WordPress plugin.
  • Improved Locale facet — flags and readable names throughout the search UI. The Locale sidebar facet now shows flag emojis and language names instead of raw locale codes: hr_hr becomes 🇭🇷 Croatian, sr_sr becomes 🇷🇸 Serbian, and so on. The top-right All Locales selector panel also displays the correct country flag beside each language group. Active locale filters — whether applied from the sidebar facet or the top-right panel — appear as removable pills labelled with flag and name. Languages without a canonical country flag (e.g. Latin, constructed codes) show a 🌐 globe icon. Applied across the Opensolr search page, Drupal module, and WordPress plugin.

Admin Apr 22, 2026

  • Improved WebCrawler — control buttons (Start/Stop Schedule, Reindex All, Reindex From Scratch, Stop Crawl, Pause/Resume, Flush to Solr) are now equal width and arranged in a clean two-column grid. Previously they were free-flowing flex items at varying widths; the container is now a two-column CSS grid so each button occupies a uniform cell.
  • Improved Index Settings — Search Mode radio buttons now sit on a single row. Previously the five options (Union, KW Required, Meaning Req., Intersection, Lexical Only) broke across two rows with the last one orphaned; the grid was widened from 4 to 5 columns so all five fit neatly side by side.

WordPress Apr 22, 2026

  • New Opensolr Search for WordPress 1.0.7 — adds the Lexical Only search mode, matching the Opensolr admin and Drupal module. Explicit opt-out from vector: no embedding API call is made, search runs through the lexical edismax path. The Minimum Relevance Score slider auto-zeroes the moment the radio is picked (backend enforces this on save and at query time as well). Yellow note in Search Mode explains the coupling.

Drupal Apr 22, 2026

  • New Opensolr Search for Drupal 3.5.0 — adds the Lexical Only search mode, matching the option in the Opensolr admin. Skips the embedding request entirely and runs pure lexical search. When selected, the Minimum Relevance Score is auto-zeroed (on save and at query time) so results aren't filtered out by a hybrid-calibrated threshold. Same feature across the stack — Opensolr admin, Drupal module, WordPress plugin.

Search Apr 22, 2026

  • New New Lexical Only search mode in Search Tuning → Search Mode. Explicit opt-out from vector — no embedding API call is made, search runs straight through the lexical edismax path. Useful for deterministic BM25 ranking, avoiding embedding API latency, or users on plans without vector who want explicit control instead of the implicit server-side fallback. When selected, the Minimum Relevance Score slider auto-zeros itself (that threshold is calibrated for the combined hybrid score; a positive value would filter out every result in pure lexical mode) and a yellow note explains the coupling.

WordPress Apr 21, 2026

  • New Opensolr Search for WordPress 1.0.5 — adds the Minimum Relevance Score slider to Search Tuning, matching the feature in the Opensolr admin and Drupal module. Drops low-scoring hybrid hits from results and facet counts, cleaning up catalog and content searches. Slider is in 0.1 increments, default 0.3.

Drupal Apr 21, 2026

  • New Opensolr Search for Drupal 3.4.0 — adds the Minimum Relevance Score slider to Search Tuning, matching the feature in the Opensolr admin. Drops low-scoring hybrid hits from results and facet counts. Slider is in 0.1 increments, default 0.3. Includes an update hook that restores the setting for sites upgrading from older versions.

Search Apr 21, 2026

  • Fix Fixed custom Minimum Match values not saving. Values containing the less-than character (e.g. 2<95% 5<90% 8<80%) were silently truncated to just the first number because the global XSS filter stripped the < before the value reached the save handler. The tuning form now reads the raw request body for this field — custom mm presets save and apply correctly.
  • Improved Search page pagination layout cleaned up — pagination is now rendered inside the results column instead of drifting to the left under the facet sidebar, and the redundant top pagination block (which appeared next to the "Did you mean" spellcheck line) has been removed. Pagination now lives only at the bottom of the results, aligned with the rest of the content.
  • New New Search Operators help button next to the Search bar. Opens a panel explaining "phrase match", +required, and -excluded operators with examples and a note on why they matter in hybrid search. Users can now refine queries like +laptop "13 inch" -refurbished and cut through semantic noise instantly.
  • New New Minimum Relevance Score slider in Search Tuning. Drops hits whose combined lexical + vector score falls below the threshold, cleaning noise out of facet counts and result totals. Essential for hybrid search on catalog-style content — without it, numFound balloons to the entire filter set and facet counts pick up docs the user would never consider relevant. Slider moves in 0.1 increments, default 0.3, 0 disables.

Analytics Apr 21, 2026

  • New Export CSV from Query Analytics — every table in the Analytics Dashboard (Popular Queries, Latest Queries, Path Distribution, Queries Over Time, Per-Server Stats) now has a green Export CSV button. Downloads are UTF-8 BOM-encoded for Excel compatibility, and the Latest Queries export respects your active filters (search, HTTP status, IP address).
  • Improved Faster Query Analytics — Popular Queries, Latest Queries, Path Distribution and Per-Server metrics now load noticeably faster across the dashboard. Historical analytics results are cached for 30 minutes (up from 5), single-hit noise is filtered out of "popular" results, and the default window for Popular/Latest Queries was expanded from 10 to 30 days so you get more context out of the box.

WordPress Apr 10, 2026

  • Fix Fixed WordPress plugin Save & Connect not registering the sitemap URL with the crawler, and Save & Start Fresh not deleting the previous index. Also added full-screen progress modal with step-by-step status and error reporting during setup, and improved product meta tag injection for WooCommerce (BreadcrumbList, price, currency, product categories).

Drupal Apr 10, 2026

  • Fix Fixed Drupal module Save & Connect not registering the sitemap URL with the crawler. The sitemap is now registered on every Save & Connect and Save & Start Fresh. Also fixed Save & Start Fresh not deleting the previous index before creating a new one. Released as 3.3.3.

Search Apr 10, 2026

  • Improved Improved hybrid search relevance — in vector hybrid mode, lexical field weight boosts are now automatically zeroed out so that semantic similarity drives the relevance ranking. Previously, even small lexical boosts could inflate scores well above the 0-1 vector range, pushing semantically relevant results down. Field weights still apply when search falls back to pure lexical mode.

WordPress Apr 9, 2026

Data Ingestion Apr 9, 2026

  • Fix Fixed Data Ingestion API endpoints returning empty responses. A PHP 8 compatibility issue in the API layer caused all ingestion, embedding, and AI endpoints to silently fail. Restored full functionality for ingest, embed, ai_summary, and all related API calls.

Search Apr 9, 2026

  • Fix Fixed Query Elevation controls not appearing on the hosted search page. Token-based authentication now accounts for CAPTCHA verification time, and elevation settings take effect immediately after toggling (previously required up to 10 minutes due to caching).

Data Ingestion Apr 9, 2026

  • Improved Data Ingestion queue dashboard redesigned for scale — indexes and jobs now load progressively on click instead of all at once. Per-index progress dialog shows real-time status for each index separately. Handles thousands of jobs without performance degradation.

Drupal Apr 9, 2026

  • Fix Fixed Query Elevation REMOVE button appearing on results with no elevation rules. Visibility now controlled via CSS class specificity instead of inline styles, fixing conflicts between button display and hide states.

Search Apr 9, 2026

  • Improved Search results count now appears directly below the search bar for immediate feedback. Response time displayed in seconds (e.g. 0.09 s) instead of milliseconds. Price and date facet sliders stay visible even when filters narrow results to a single item.

Data Ingestion Apr 9, 2026

  • Improved Improved Data Ingestion enrichment pipeline — embeddings now use structured text (text_t) when available for richer semantic vectors. Sentiment analysis uses first 10 complete sentences instead of just title + description. Document size field now computed automatically.
  • Fix Fixed duplicate documents when using both Web Crawler and Data Ingestion on the same index. URIs are now normalized (trailing slash stripped) before computing the document ID, so both methods produce the same document instead of duplicates.

Documentation Apr 9, 2026

WordPress Apr 9, 2026

Drupal Apr 4, 2026

  • New Drupal Module Partner Program — get 50% off any small or medium plan for a full year by installing and actively using the free Opensolr Search Drupal module. Provide feedback, suggestions, or bug reports in exchange. Apply from the pricing page.

Search Apr 4, 2026

  • Improved Price filter topbar slider tooltips now show thousands separators (e.g. 15,638.00 instead of 15638.00). Consistent number formatting across all slider controls, tooltips, and input fields.

Drupal Apr 4, 2026

  • Fix Safari and iOS compatibility — fixed show-more buttons, async noUiSlider loading, expand dialog z-index above Drupal toolbar, mobile overflow handling. Show-more dialogs now use event delegation for reliable touch behavior.
  • Improved Per-facet minimum count threshold — configure how many documents a facet value needs before it appears. Instant CSS tooltips on facet hover replace slow browser title popups. Facet values preserve original casing from the source data.
  • New Hierarchical drill-down facets — navigate multi-level taxonomies like breadcrumbs (e.g. Products > Electrical testing > Clamp meters). Auto-detected from JSON-LD BreadcrumbList data. Supports starting from any level and "Show more" for large lists.

Web Crawler Apr 4, 2026

  • Improved Improved web crawler date extraction for sites that lack JSON-LD or meta tags. New targeted extraction looks for dates inside HTML elements with date-related CSS classes (e.g. .date, .posted, .info) — much safer than scanning all page text.
  • Fix Fixed date indexing errors caused by timezone offsets (e.g. +03:00) in date fields. All dates are now strictly converted to UTC before sending to Solr. Added a final safety gate — any date that doesn't match the exact Solr format is dropped rather than causing an indexing error.

Search Apr 4, 2026

  • Improved Active filter pills now show numbers with thousands separators (e.g. "Price from: 9,507.99" instead of "9507.99"). Applies to both the facet sidebar pills and the topbar price filter pills.
  • Improved Facet slider inputs now display numbers with thousands separators (e.g. 15,637.00 instead of 15637.00) for better readability. Float fields (_f) show 2 decimals, integer fields show none. Min values are floored and max values are ceiled so the range always covers all results.

Website Apr 3, 2026

  • Improved Homepage Drupal card updated — now showcases the Opensolr Search for Drupal module with full-text search, facets, analytics, and AI features. New vector search e-commerce demo added to the live demos section.

Web Crawler Apr 3, 2026

  • Improved Web Crawler now respects the package's vector access flag — indexes without AI features skip embedding generation during crawls, saving GPU resources and speeding up indexing.

Control Panel Apr 3, 2026

  • New Search Facet Filters configuration section in the admin panel — discover all indexed fields via Solr schema, map them as list, slider, or date range widgets, drag to reorder. Embeddable search also supports facets via data-sidebar="on".

Performance & SEO Apr 3, 2026

  • Improved GPU priority queue for AI embeddings — user-facing search requests now always jump ahead of background crawler batch jobs. Prevents slow search during heavy indexing. Includes a configurable timeout so search falls back to lexical instantly if the GPU is busy.

API Apr 3, 2026

  • New AI and vector features (AI Hints, AI Reader, Vector Embeddings, Hybrid Search) are now gated per package. Indexes without vector access get a friendly upgrade prompt instead of a generic error. Lexical keyword search continues to work on every plan.

Search Apr 3, 2026

  • Fix Fixed search result highlighting — switched to a more reliable highlighter that correctly highlights keywords in short fields like titles. Also added text_t (structured text) to highlighted fields for richer snippets.
  • Improved Search header now stays fixed at the top while scrolling through results, keeping the search box and controls always within reach.
  • Improved Search transitions now show a loading overlay with animated dots, so you know the search is working — especially helpful on slower connections or large indexes.
  • New Facet filter sidebar — filter search results by category, price, date, and any structured field. Supports list facets, numeric sliders, and date range pickers. "Show more" dialog with letter index for browsing large facet lists. Active filters shown as removable pills. Configure facets from the admin panel under Search Facet Filters.
123>
Page 1 of 3