OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.
Python
fix: improve search fallback matching and aggregation consistency
Olfa Maslah2ec72be84145
diff --git a/src/services/search_service.py b/src/services/search_service.pyindex 0ac9c3e1b..4bd771ec4 100644--- a/src/services/search_service.py+++ b/src/services/search_service.py@@ -1,5 +1,6 @@import copyimport json+from collections import Counterfrom typing import Any, Dictfrom config.settings import EMBED_MODEL, clients, get_embedding_model, get_index_name, WATSONX_EMBEDDING_DIMENSIONSfrom auth_context import get_auth_context@@ -315,19 +316,23 @@ class SearchService:"query": query,"fields": ["text^2", "filename^1.5"],"type": "best_fields",- "operator": "and",+ "operator": "or","fuzziness": "AUTO:4,7","boost": 0.3, # 30% weight for keyword search}},{- # Help prefix/partial inputs (e.g. "vita" -> "vitamin")- # without making the whole query fully fuzzy.- "multi_match": {- "query": query,- "fields": ["text^1.5", "filename^2"],- "type": "bool_prefix",- "boost": 0.25,+ # Prefix fallback for partial input (e.g. "vita" -> "vitamin").+ # Avoid bool_prefix here because our current mappings are:+ # - text: standard "text" (not search_as_you_type / edge-ngram)+ # - filename: "keyword"+ # match_phrase_prefix with a bounded expansion is safer.+ "match_phrase_prefix": {+ "text": {+ "query": query,+ "max_expansions": 50,+ "boost": 0.25,+ }}},],@@ -493,6 +498,7 @@ class SearchService:# If query text appears verbatim in one subset of files, prefer those files# to avoid broad semantic spillover for unique lookups.normalized_query = query.strip().lower()+ aggregations = results.get("aggregations", {})if (normalized_queryand not is_wildcard_match_all@@ -514,10 +520,36 @@ class SearchService:if exact_files:chunks = [chunk for chunk in chunks if chunk.get("filename") in exact_files]+ def _build_terms_agg(field: str) -> Dict[str, Any]:+ counts = Counter(+ value+ for chunk in chunks+ for value in [chunk.get(field)]+ if isinstance(value, str) and value+ )+ return {+ "doc_count_error_upper_bound": 0,+ "sum_other_doc_count": 0,+ "buckets": [+ {"key": key, "doc_count": count}+ for key, count in counts.most_common()+ ],+ }++ # Keep aggregations consistent with the post-filtered result set.+ aggregations = {+ **aggregations,+ "data_sources": _build_terms_agg("filename"),+ "document_types": _build_terms_agg("mimetype"),+ "owners": _build_terms_agg("owner"),+ "connector_types": _build_terms_agg("connector_type"),+ "embedding_models": _build_terms_agg("embedding_model"),+ }+# Return both transformed results and aggregationsreturn {"results": chunks,- "aggregations": results.get("aggregations", {}),+ "aggregations": aggregations,"total": len(chunks),}