opensolr-haystack 0.2.8__tar.gz → 0.2.9__tar.gz

{opensolr_haystack-0.2.8 → opensolr_haystack-0.2.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opensolr-haystack
-Version: 0.2.8
+Version: 0.2.9
 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

{opensolr_haystack-0.2.8 → opensolr_haystack-0.2.9}/haystack_integrations/document_stores/opensolr/client.py

@@ -10,6 +10,7 @@ Direct Solr access (select/update) goes to the index's own host, resolved via
 
 from __future__ import annotations
 
+import re
 import json
 from typing import Any, Dict, List, Optional, Tuple
 
@@ -392,11 +393,19 @@ class OpensolrClient:
 
         parts: List[str] = []
         for doc in hits[:docs]:
-            text_words = _flat(doc.get("text")).split()[:words]
+            # Truncate at the Nth word by CUTTING the original string, never by splitting and
+            # re-joining: " ".join(text.split()) throws away every newline and every run of
+            # indentation, so a page arrives as one unbroken line with its paragraphs, lists and
+            # code blocks flattened. Text handed to a model has to reach it as written; the
+            # structure is part of the meaning (2026-08-26).
+            body = _flat(doc.get("text"))
+            matches = list(re.finditer(r"\S+", body))
+            if len(matches) > words:
+                body = body[: matches[words - 1].end()]
             parts.append(
-                _flat(doc.get("title")) + " - "
-                + _flat(doc.get("description")) + " - "
-                + " ".join(text_words) + " - "
+                _flat(doc.get("title")) + "\n"
+                + _flat(doc.get("description")) + "\n"
+                + body + "\n\n"
             )
         return "".join(parts)
 

{opensolr_haystack-0.2.8 → opensolr_haystack-0.2.9}/opensolr_haystack.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opensolr-haystack
-Version: 0.2.8
+Version: 0.2.9
 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

{opensolr_haystack-0.2.8 → opensolr_haystack-0.2.9}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "opensolr-haystack"
-version = "0.2.8"
+version = "0.2.9"
 description = "Haystack integration for Opensolr — managed Apache Solr DocumentStore with server-side embeddings and hybrid BM25+kNN retrieval"
 readme = "README.md"
 license = { text = "MIT" }