refactor

.env

-
-ASTRA_DB_API_ENDPOINT="https://0c52512b-0c65-4e70-ac47-71edf5244a82-us-east-2.apps.astra.datastax.com"
-ASTRA_DB_APPLICATION_TOKEN="AstraCS:EvXpFFafufegdQJvhqlYxmxt:ef86b5996013b12140b69254bd554d7e8e10eb5a7137859b9c432f92a5a3b65c"
+ASTRA_DB_API_ENDPOINT="https://9706ee0b-b3e8-4ee2-bb26-45e8a0db1586-us-east-2.apps.astra.datastax.com"
+ASTRA_DB_APPLICATION_TOKEN="AstraCS:OEbpcggZbUjOvRiesULZkTnf:9d215d8d32c2ffb09081212208e474f81a0bcdde45e7b683cd67f4a1a936a8bf"
 ASTRA_DB_NAMESPACE="default_keyspace"
-HF_TOKEN="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"
-GROQ_API_KEY="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"
+HF_TOKEN="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"
+GROQ_API_KEY="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"
+HUGGING_FACE_MODEL="BAAI/bge-base-en-v1.5"
\ No newline at end of file

poetry.lock

@@ -2494,6 +2494,17 @@ files = [
 [package.dependencies]
 requests = ">=2.0.1,<3.0.0"
 
+[[package]]
+name = "review"
+version = "1510"
+description = "upload script for Rietveld code review tool"
+optional = false
+python-versions = "*"
+groups = ["main"]
+files = [
+    {file = "review-1510.zip", hash = "sha256:0b49c9c80dfaf051b399d9147a76f0900edab95ee3816d2a4c1a3c3a6ad130f9"},
+]
+
 [[package]]
 name = "safetensors"
 version = "0.5.2"
@@ -3287,4 +3298,4 @@ propcache = ">=0.2.0"
 [metadata]
 lock-version = "2.1"
 python-versions = "^3.9"
-content-hash = "a980d3a86400e70c44fece09364c23407b1a898daad559746447df6ff7773437"
+content-hash = "b7e83229a21b0e3036ab39dbca747be37a094792b9352cd6f141348e36666d42"

pyproject.toml

@@ -17,6 +17,7 @@ transformers = "^4.30.0"
 numpy = "^1.24.0"
 pydantic = "^2.10.6"
 langchain_groq = "^0.1.10"
+review = "^1510"
 
 
 [tool.poetry.dev-dependencies]

src/reviewsense/api/routes.py

 from fastapi import APIRouter, HTTPException
 from typing import Dict, Optional
 
-from reviewsense.api.schemas.UserMessage import UserMessage
-from reviewsense.api.schemas.product_review_input import ProductReviewInput
-from reviewsense.services.BotService import BotService
-from reviewsense.services.ReviewService import ReviewService
 
 
+
+from src.reviewsense.api.schemas.UserMessage import UserMessage
+from src.reviewsense.services.BotService import BotService
+
 router = APIRouter()
-review_service = ReviewService()
 
 @router.post("/calculate_ratings/", response_model=Dict[str, Optional[float]])
 

src/reviewsense/main.py

 from fastapi import FastAPI
 from reviewsense.api.routes import router
-from reviewsense.core.config import get_settings
+
 from fastapi.middleware.cors import CORSMiddleware
 
 def create_app() -> FastAPI:

src/reviewsense/services/BotService.py

@@ -5,11 +5,9 @@ from langchain_astradb import AstraDBVectorStore
 from logging import getLogger
 from functools import lru_cache
 
-from langchain_core.output_parsers import JsonOutputParser
-from langchain_core.prompts import ChatPromptTemplate
 
-from reviewsense.core.llm import get_llm, generate_response
-from reviewsense.services.retrieval import get_vector_store
+from src.reviewsense.core.llm import generate_response, get_llm
+from src.reviewsense.services.retrieval import get_vector_store
 
 logger = getLogger(__name__)
 
@@ -79,16 +77,17 @@ class BotService:
             ProductContext if found, None otherwise
         """
         try:
-            as_retriever = self.vector_store.as_retriever(search_type="similarity_score_threshold",
-                                                          search_kwargs={"k": 1, "score_threshold": 0.8}, )
-            results = as_retriever.invoke(search_query)
+            # as_retriever = self.vector_store.as_retriever(search_type="similarity_score_threshold",
+            #                                               search_kwargs={"k": 1, "score_threshold": 0.8}, )
+            documents = self.vector_store.similarity_search_with_score(query="good camera", k=100)
+            # results = as_retriever.invoke(search_query)
+
+            # if not results:
+            #     logger.info("No results found for query")
+            #     return None
 
-            if not results:
-                logger.info("No results found for query")
-                return None
 
-            document = results[0]
-            product_name = document.metadata.get('product_name')
+            product_name = documents[0][0].metadata.get('title')
 
             if not product_name:
                 logger.warning("Product name missing in document metadata")
@@ -132,3 +131,39 @@ class BotService:
         except BotServiceError as e:
             logger.error(f"Error handling user query: {e}")
             return "I apologize, but I encountered an error processing your request."
+
+    def get_product_reviews(
+            self,
+            product_id: str,
+            query: str,
+            k: int = 1
+    ) -> str:
+        """
+        Retrieve and combine product reviews from the vector store.
+
+        Args:
+            product_id: Product identifier
+            query: Search query
+            k: Number of results to retrieve
+
+        Returns:
+            Combined review string
+        """
+        try:
+            results = self.vector_store.similarity_search_with_score_id(
+                query=query,
+                k=5,
+                filter={"title": product_id}
+            )
+
+            all_reviews = []
+            for doc, _, _ in results:
+                reviews = ReviewProcessor.process_reviews(doc.page_content)
+                all_reviews.extend(reviews)
+
+            return ' '.join(all_reviews)
+
+        except Exception as e:
+            logger.error(f"Error retrieving product reviews: {e}")
+            raise VectorStoreError(f"Failed to retrieve reviews: {e}")
+

src/reviewsense/services/retrieval.py

 # src/reviewsense/core/database.py
 from functools import lru_cache
+from dotenv import load_dotenv
+import os
 
 from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_astradb import AstraDBVectorStore
-from reviewsense.core.config import get_settings
+
+load_dotenv()
+huggingface_inference_api = os.getenv("HF_TOKEN")
+huggingface_model = os.getenv("HUGGING_FACE_MODEL")
+astra_db_api_end_point = os.getenv("ASTRA_DB_API_END_POINT")
+astra_db_token = os.getenv("ASTRA_DB_TOKEN")
+astra_db_name_space = os.getenv("ASTRA_DB_NAME_SPACE")
+
 
 @lru_cache(maxsize=1)
 def get_vector_store(
-    collection_name: str = "One",
-    embedding_model: str = "sentence-transformers/all-mpnet-base-v2"
+        collection_name: str = "customer_reviews",
+        embedding_model: str = "sentence-transformers/all-mpnet-base-v2"
 ):
     """
     Create a singleton vector store instance
-    
+
     Args:
         collection_name (str): Database collection name
         embedding_model (str): Embedding model to use
-    
+
     Returns:
         AstraDBVectorStore: Configured vector store instance
     """
-    settings = get_settings()
-    
+
     # Initialize embeddings
-    embeddings = HuggingFaceInferenceAPIEmbeddings(api_key="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", model_name="BAAI/bge-base-en-v1.5")
-    
+    embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=huggingface_inference_api, model_name=huggingface_model)
+
     # Create and return vector store
     return AstraDBVectorStore(
         collection_name=collection_name,
         embedding=embeddings,
-        api_endpoint="https://9706ee0b-b3e8-4ee2-bb26-45e8a0db1586-us-east-2.apps.astra.datastax.com",
-        token="AstraCS:OEbpcggZbUjOvRiesULZkTnf:9d215d8d32c2ffb09081212208e474f81a0bcdde45e7b683cd67f4a1a936a8bf",
-        namespace="default_keyspace",
+        api_endpoint=astra_db_api_end_point,
+        token=astra_db_token,
+        namespace=astra_db_name_space,
     )
\ No newline at end of file