update to configuration

app.py

@@ -1,13 +1,13 @@
 from fastapi import FastAPI
 from neural_searcher import NeuralSearcher
+from huggingface_hub import login
+import os
 
-app = FastAPI()
+login(os.getenv('HUGGING_FACE_API_KEY'))
 
-neural_searcher = NeuralSearcher(collection_name="odluke-demo")
+app = FastAPI()
 
-@app.get("/")
-async def root():
-    return {"message": "Hello World"}
+neural_searcher = NeuralSearcher(collection_name=os.getenv('COLLECTION_NAME'))
 
 @app.get("/api/search")
 def search_startup(q: str):

neural_searcher.py

@@ -1,46 +1,41 @@
 from qdrant_client import QdrantClient
 from fastembed import SparseTextEmbedding
-from huggingface_hub import login
-import os
 from qdrant_client import QdrantClient, models
 from sentence_transformers import SentenceTransformer
+import os
 
-# from config import API_KEY,HOST,DENSE_MODEL,SPARSE_MODEL,DENSE_MODEL_SHORT,SPARSE_MODEL_SHORT
 class NeuralSearcher:
 
     def __init__(self, collection_name):
         self.collection_name = collection_name
-        self.dense_model = SentenceTransformer("dzenzzz/mne-lawic",device="cpu")
-        self.sparse_model = SparseTextEmbedding("Qdrant/bm25")
-        # self.qdrant_client = QdrantClient("http://localhost:6333/",api_key="")
+        self.dense_model = SentenceTransformer(os.getenv('DENSE_MODEL'),device="cpu")
+        self.sparse_model = SparseTextEmbedding(os.getenv('SPARSE_MODEL'))
+        self.qdrant_client = QdrantClient(os.getenv('QDRANT_URL'),api_key=os.getenv('QDRANT_API_KEY'))
     
-    login(os.getenv('HUGGING_FACE_API_KEY'))
-
     def search(self, text: str):
   
         dense_query = self.dense_model.encode(text).tolist()
         sparse_query = self.sparse_model.query_embed(text)
         
-        # # Use `vector` for search for closest vectors in the collection
-        # search_result = self.qdrant_client.query_points(
-        #     collection_name= self.collection_name,
-        #     prefetch=[
-        #         models.Prefetch(
-        #             query=dense_query,
-        #             using="djovak/embedic-small",
-        #             limit=5
-        #         ),
-        #         models.Prefetch(
-        #             query=next(sparse_query).as_object(),
-        #             using="Qdrant/bm25",
-        #             limit=5
-        #         )
-        #     ],
-        #     query=models.FusionQuery(
-        #         fusion=models.Fusion.RRF
-        #     ),
-        #     limit = 9
-        # ).points
+        search_result = self.qdrant_client.query_points(
+            collection_name= self.collection_name,
+            prefetch=[
+                models.Prefetch(
+                    query=dense_query,
+                    using=os.getenv('DENSE_MODEL'),
+                    limit=5
+                ),
+                models.Prefetch(
+                    query=next(sparse_query).as_object(),
+                    using=os.getenv('SPARSE_MODEL'),
+                    limit=5
+                )
+            ],
+            query=models.FusionQuery(
+                fusion=models.Fusion.RRF
+            ),
+            limit = 9
+        ).points
 
-        # payloads = [hit.payload for hit in search_result]
-        return dense_query
+        payloads = [hit.payload for hit in search_result]
+        return payloads