Merge branch 'dev' into fix-db-order

backend/open_webui/retrieval/loaders/main.py

@@ -105,7 +105,7 @@ class TikaLoader:
 
         if r.ok:
             raw_metadata = r.json()
-            text = raw_metadata.get("X-TIKA:content", "<No text content found>")
+            text = raw_metadata.get("X-TIKA:content", "<No text content found>").strip()
 
             if "Content-Type" in raw_metadata:
                 headers["Content-Type"] = raw_metadata["Content-Type"]

backend/open_webui/retrieval/utils.py

@@ -106,6 +106,7 @@ def query_doc_with_hybrid_search(
     embedding_function,
     k: int,
     reranking_function,
+    k_reranker: int,
     r: float,
 ) -> dict:
     try:
@@ -128,7 +129,7 @@ def query_doc_with_hybrid_search(
         )
         compressor = RerankCompressor(
             embedding_function=embedding_function,
-            top_n=k,
+            top_n=k_reranker,
             reranking_function=reranking_function,
             r_score=r,
         )
@@ -138,10 +139,20 @@ def query_doc_with_hybrid_search(
         )
 
         result = compression_retriever.invoke(query)
+
+        distances = [d.metadata.get("score") for d in result]
+        documents = [d.page_content for d in result]
+        metadatas = [d.metadata for d in result]
+
+        # retrieve only min(k, k_reranker) items, sort and cut by distance if k < k_reranker
+        if k < k_reranker:
+            sorted_items = sorted(zip(distances, metadatas, documents), key=lambda x: x[0], reverse=True)
+            sorted_items = sorted_items[:k]
+            distances, documents, metadatas = map(list, zip(*sorted_items))
         result = {
-            "distances": [[d.metadata.get("score") for d in result]],
-            "documents": [[d.page_content for d in result]],
-            "metadatas": [[d.metadata for d in result]],
+            "distances": [distances],
+            "documents": [documents],
+            "metadatas": [metadatas],
         }
 
         log.info(
@@ -264,6 +275,7 @@ def query_collection_with_hybrid_search(
     embedding_function,
     k: int,
     reranking_function,
+    k_reranker: int,
     r: float,
 ) -> dict:
     results = []
@@ -277,6 +289,7 @@ def query_collection_with_hybrid_search(
                     embedding_function=embedding_function,
                     k=k,
                     reranking_function=reranking_function,
+                    k_reranker=k_reranker,
                     r=r,
                 )
                 results.append(result)
@@ -290,10 +303,8 @@ def query_collection_with_hybrid_search(
         raise Exception(
             "Hybrid search failed for all collections. Using Non hybrid search as fallback."
         )
-
     return merge_and_sort_query_results(results, k=k)
 
-
 def get_embedding_function(
     embedding_engine,
     embedding_model,
@@ -337,6 +348,7 @@ def get_sources_from_files(
     embedding_function,
     k,
     reranking_function,
+    k_reranker,
     r,
     hybrid_search,
     full_context=False,
@@ -453,6 +465,7 @@ def get_sources_from_files(
                                     embedding_function=embedding_function,
                                     k=k,
                                     reranking_function=reranking_function,
+                                    k_reranker=k_reranker,
                                     r=r,
                                 )
                             except Exception as e:

backend/open_webui/retrieval/vector/dbs/chroma.py

@@ -172,12 +172,19 @@ class ChromaClient:
         filter: Optional[dict] = None,
     ):
         # Delete the items from the collection based on the ids.
-        collection = self.client.get_collection(name=collection_name)
-        if collection:
-            if ids:
-                collection.delete(ids=ids)
-            elif filter:
-                collection.delete(where=filter)
+        try:
+            collection = self.client.get_collection(name=collection_name)
+            if collection:
+                if ids:
+                    collection.delete(ids=ids)
+                elif filter:
+                    collection.delete(where=filter)
+        except Exception as e:
+            # If collection doesn't exist, that's fine - nothing to delete
+            log.debug(
+                f"Attempted to delete from non-existent collection {collection_name}. Ignoring."
+            )
+            pass
 
     def reset(self):
         # Resets the database. This will delete all collections and item entries.