opensolr-haystack 0.2.4__tar.gz → 0.2.6__tar.gz

{opensolr_haystack-0.2.4 → opensolr_haystack-0.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opensolr-haystack
-Version: 0.2.4
+Version: 0.2.6
 Summary: Haystack integration for Opensolr — managed Apache Solr DocumentStore with server-side embeddings and hybrid BM25+kNN retrieval
 Author-email: Opensolr <support@opensolr.com>
 License: MIT
@@ -22,6 +22,8 @@ Dynamic: license-file
 [Opensolr](https://opensolr.com) — managed Apache Solr as a DocumentStore,
 with **server-side embeddings** and native **hybrid (BM25 + kNN) retrieval**.
 
+**See it live (real news index, hybrid + AI answer):** https://search.opensolr.com/news__dense?q=how+am+I+supposed+to+save+money%3F
+
 No embedder components needed in your pipeline — texts and queries are
 embedded on Opensolr's GPU infrastructure (multilingual E5-large-instruct,
 1024 dimensions, cosine).
@@ -98,8 +100,10 @@ Writes go through Opensolr's [Data Ingestion API](https://opensolr.com/learn/api
 — the same pipeline the Drupal and WordPress connectors use. It is
 **asynchronous**: documents are queued, then embeddings, sentiment, language
 and all crawler-identical derived fields are computed **server-side**, and
-documents become searchable within about a minute. Progress is visible in the
-Opensolr Control Panel and via the `ingest_status` API. Each document's
+documents become searchable within about a minute. Progress is visible in
+**Control Panel → Data Ingestion** — a per-job status board (queued /
+processing / completed / failed, with processed / success / failed document
+counts per job) — and via the `ingest_status` API. Each document's
 identity is its `uri` (the Solr id is `md5(uri)`): pass a real URL in
 metadata (`{"uri": "https://..."}`), or a deterministic one is synthesized
 from your id. Re-submitting the same `uri` updates the document. Pass

{opensolr_haystack-0.2.4 → opensolr_haystack-0.2.6}/README.md

@@ -4,6 +4,8 @@
 [Opensolr](https://opensolr.com) — managed Apache Solr as a DocumentStore,
 with **server-side embeddings** and native **hybrid (BM25 + kNN) retrieval**.
 
+**See it live (real news index, hybrid + AI answer):** https://search.opensolr.com/news__dense?q=how+am+I+supposed+to+save+money%3F
+
 No embedder components needed in your pipeline — texts and queries are
 embedded on Opensolr's GPU infrastructure (multilingual E5-large-instruct,
 1024 dimensions, cosine).
@@ -80,8 +82,10 @@ Writes go through Opensolr's [Data Ingestion API](https://opensolr.com/learn/api
 — the same pipeline the Drupal and WordPress connectors use. It is
 **asynchronous**: documents are queued, then embeddings, sentiment, language
 and all crawler-identical derived fields are computed **server-side**, and
-documents become searchable within about a minute. Progress is visible in the
-Opensolr Control Panel and via the `ingest_status` API. Each document's
+documents become searchable within about a minute. Progress is visible in
+**Control Panel → Data Ingestion** — a per-job status board (queued /
+processing / completed / failed, with processed / success / failed document
+counts per job) — and via the `ingest_status` API. Each document's
 identity is its `uri` (the Solr id is `md5(uri)`): pass a real URL in
 metadata (`{"uri": "https://..."}`), or a deterministic one is synthesized
 from your id. Re-submitting the same `uri` updates the document. Pass

{opensolr_haystack-0.2.4 → opensolr_haystack-0.2.6}/haystack_integrations/document_stores/opensolr/client.py

@@ -42,6 +42,29 @@ def resolve_location(location: str) -> str:
 BATCH_EMBED_MAX = 50
 
 
+# Default RAG instruction (added 2026-08-25).
+# Without an instruction the server falls back to "Answer the query based on
+# the context", which makes the model hedge: it opens with a disclaimer that
+# the context does not cover the question and then answers it anyway. These
+# rules make it lead with the answer and keep the concrete details. Callers
+# can still override everything by passing ``instruction``.
+DEFAULT_RAG_INSTRUCTION = (
+    "Answer the query using only the context below. "
+    "Do not repeat or restate the question, and do not print it as a heading. "
+    "If the question is a yes or no question and the context supports it, begin with \"Yes\". "
+    "For any other question, begin with the fact itself, never with \"Yes\". "
+    "Never begin with \"No\" when the context does support the answer. "
+    "Start with the answer itself: do not open with a preamble about what the context does "
+    "or does not address, and never say the context does not cover the query and then answer "
+    "it anyway. "
+    "Give a substantive answer with the concrete details from the context: who, what, where "
+    "and when. "
+    "Do not dismiss the query on a technicality. If the context covers something closely "
+    "related rather than the exact wording used, explain what it does say and how it relates. "
+    "Only if nothing in the context is relevant at all, say so in one sentence and name what "
+    "the context is about instead."
+)
+
 class OpensolrError(RuntimeError):
     """Raised when an Opensolr API call fails."""
 
@@ -353,6 +376,16 @@ class OpensolrClient:
                 index, query, rows=docs, fl="title,description,text", fq=fq
             )
             hits = body.get("response", {}).get("docs", [])
+        # Relevance floor (2026-08-25). Retrieval always returns `docs` hits, so a
+        # narrow question arrives with one good match and several unrelated ones.
+        # The model then sees that most of its context does not answer the query
+        # and hedges. Drop anything scoring below half of the best hit; documents
+        # without a score are kept, since only provable weakness is filtered.
+        scored = [float(h["score"]) for h in hits if isinstance(h, dict) and h.get("score") is not None]
+        if scored:
+            floor = max(scored) * 0.5
+            hits = [h for h in hits if h.get("score") is None or float(h["score"]) >= floor]
+
         parts: List[str] = []
         for doc in hits[:docs]:
             text_words = _flat(doc.get("text")).split()[:words]
@@ -390,8 +423,7 @@ class OpensolrClient:
             "stream": "false",
             **params,
         }
-        if instruction:
-            data["instruction"] = instruction
+        data["instruction"] = instruction or DEFAULT_RAG_INSTRUCTION
         if "context" not in data:
             try:
                 context = self._rag_context(

{opensolr_haystack-0.2.4 → opensolr_haystack-0.2.6}/opensolr_haystack.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opensolr-haystack
-Version: 0.2.4
+Version: 0.2.6
 Summary: Haystack integration for Opensolr — managed Apache Solr DocumentStore with server-side embeddings and hybrid BM25+kNN retrieval
 Author-email: Opensolr <support@opensolr.com>
 License: MIT
@@ -22,6 +22,8 @@ Dynamic: license-file
 [Opensolr](https://opensolr.com) — managed Apache Solr as a DocumentStore,
 with **server-side embeddings** and native **hybrid (BM25 + kNN) retrieval**.
 
+**See it live (real news index, hybrid + AI answer):** https://search.opensolr.com/news__dense?q=how+am+I+supposed+to+save+money%3F
+
 No embedder components needed in your pipeline — texts and queries are
 embedded on Opensolr's GPU infrastructure (multilingual E5-large-instruct,
 1024 dimensions, cosine).
@@ -98,8 +100,10 @@ Writes go through Opensolr's [Data Ingestion API](https://opensolr.com/learn/api
 — the same pipeline the Drupal and WordPress connectors use. It is
 **asynchronous**: documents are queued, then embeddings, sentiment, language
 and all crawler-identical derived fields are computed **server-side**, and
-documents become searchable within about a minute. Progress is visible in the
-Opensolr Control Panel and via the `ingest_status` API. Each document's
+documents become searchable within about a minute. Progress is visible in
+**Control Panel → Data Ingestion** — a per-job status board (queued /
+processing / completed / failed, with processed / success / failed document
+counts per job) — and via the `ingest_status` API. Each document's
 identity is its `uri` (the Solr id is `md5(uri)`): pass a real URL in
 metadata (`{"uri": "https://..."}`), or a deterministic one is synthesized
 from your id. Re-submitting the same `uri` updates the document. Pass

{opensolr_haystack-0.2.4 → opensolr_haystack-0.2.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "opensolr-haystack"
-version = "0.2.4"
+version = "0.2.6"
 description = "Haystack integration for Opensolr — managed Apache Solr DocumentStore with server-side embeddings and hybrid BM25+kNN retrieval"
 readme = "README.md"
 license = { text = "MIT" }