Merge branch 'open-webui:main' into feat-milvus-diskann-support

backend/open_webui/retrieval/utils.py

@@ -127,7 +127,13 @@ def query_doc_with_hybrid_search(
     hybrid_bm25_weight: float,
 ) -> dict:
     try:
-        if not collection_result.documents[0]:
+        if (
+            not collection_result
+            or not hasattr(collection_result, "documents")
+            or not collection_result.documents
+            or len(collection_result.documents) == 0
+            or not collection_result.documents[0]
+        ):
             log.warning(f"query_doc_with_hybrid_search:no_docs {collection_name}")
             return {"documents": [], "metadatas": [], "distances": []}
 

backend/open_webui/retrieval/web/ollama.py

@@ -0,0 +1,51 @@
+import logging
+from dataclasses import dataclass
+from typing import Optional
+
+import requests
+from open_webui.env import SRC_LOG_LEVELS
+from open_webui.retrieval.web.main import SearchResult
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+def search_ollama_cloud(
+    url: str,
+    api_key: str,
+    query: str,
+    count: int,
+    filter_list: Optional[list[str]] = None,
+) -> list[SearchResult]:
+    """Search using Ollama Search API and return the results as a list of SearchResult objects.
+
+    Args:
+        api_key (str): A Ollama Search API key
+        query (str): The query to search for
+        count (int): Number of results to return
+        filter_list (Optional[list[str]]): List of domains to filter results by
+    """
+    log.info(f"Searching with Ollama for query: {query}")
+
+    headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
+    payload = {"query": query, "max_results": count}
+
+    try:
+        response = requests.post(f"{url}/api/web_search", headers=headers, json=payload)
+        response.raise_for_status()
+        data = response.json()
+
+        results = data.get("results", [])
+        log.info(f"Found {len(results)} results")
+
+        return [
+            SearchResult(
+                link=result.get("url", ""),
+                title=result.get("title", ""),
+                snippet=result.get("content", ""),
+            )
+            for result in results
+        ]
+    except Exception as e:
+        log.error(f"Error searching Ollama: {e}")
+        return []

backend/open_webui/retrieval/web/perplexity_search.py

@@ -0,0 +1,64 @@
+import logging
+from typing import Optional, Literal
+import requests
+
+from open_webui.retrieval.web.main import SearchResult, get_filtered_results
+from open_webui.env import SRC_LOG_LEVELS
+
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+def search_perplexity_search(
+    api_key: str,
+    query: str,
+    count: int,
+    filter_list: Optional[list[str]] = None,
+) -> list[SearchResult]:
+    """Search using Perplexity API and return the results as a list of SearchResult objects.
+
+    Args:
+      api_key (str): A Perplexity API key
+      query (str): The query to search for
+      count (int): Maximum number of results to return
+      filter_list (Optional[list[str]]): List of domains to filter results
+
+    """
+
+    # Handle PersistentConfig object
+    if hasattr(api_key, "__str__"):
+        api_key = str(api_key)
+
+    try:
+        url = "https://api.perplexity.ai/search"
+
+        # Create payload for the API call
+        payload = {
+            "query": query,
+            "max_results": count,
+        }
+
+        headers = {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json",
+        }
+
+        # Make the API request
+        response = requests.request("POST", url, json=payload, headers=headers)
+        # Parse the JSON response
+        json_response = response.json()
+
+        # Extract citations from the response
+        results = json_response.get("results", [])
+
+        return [
+            SearchResult(
+                link=result["url"], title=result["title"], snippet=result["snippet"]
+            )
+            for result in results
+        ]
+
+    except Exception as e:
+        log.error(f"Error searching with Perplexity Search API: {e}")
+        return []