From 5ded394e435bb34b955f0b21f7562e2949eb3024 Mon Sep 17 00:00:00 2001
From: Parth Patel <64201651+parthbs@users.noreply.github.com>
Date: Tue, 25 Mar 2025 19:01:01 +0000
Subject: [PATCH] #249 feat: add support for local qdrant client

---
 .../qdrant_vector_search_tool/qdrant_search_tool.py | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py b/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py
index c59dd29d5..3ef467264 100644
--- a/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py
+++ b/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py
@@ -66,8 +66,8 @@ class QdrantVectorSearchTool(BaseTool):
         ...,
         description="The URL of the Qdrant server",
     )
-    qdrant_api_key: str = Field(
-        ...,
+    qdrant_api_key: Optional[str] = Field(
+        default=None,
         description="The API key for the Qdrant server",
     )
     custom_embedding_fn: Optional[callable] = Field(
@@ -80,7 +80,7 @@ class QdrantVectorSearchTool(BaseTool):
         if QDRANT_AVAILABLE:
             self.client = QdrantClient(
                 url=self.qdrant_url,
-                api_key=self.qdrant_api_key,
+                api_key=self.qdrant_api_key if self.qdrant_api_key else None,
             )
         else:
             import click
@@ -133,7 +133,7 @@ class QdrantVectorSearchTool(BaseTool):
 
         # Search in Qdrant using the built-in query method
         query_vector = (
-            self._vectorize_query(query)
+            self._vectorize_query(query, embedding_model="text-embedding-3-large")
             if not self.custom_embedding_fn
             else self.custom_embedding_fn(query)
         )
@@ -158,11 +158,12 @@ class QdrantVectorSearchTool(BaseTool):
 
         return json.dumps(results, indent=2)
 
-    def _vectorize_query(self, query: str) -> list[float]:
+    def _vectorize_query(self, query: str, embedding_model: str) -> list[float]:
         """Default vectorization function with openai.
 
         Args:
             query (str): The query to vectorize
+            embedding_model (str): The embedding model to use
 
         Returns:
             list[float]: The vectorized query
@@ -173,7 +174,7 @@ class QdrantVectorSearchTool(BaseTool):
         embedding = (
             client.embeddings.create(
                 input=[query],
-                model="text-embedding-3-small",
+                model=embedding_model,
             )
             .data[0]
             .embedding