remove the vector db code

.idea/misc.xml

@@ -3,5 +3,5 @@
   <component name="Black">
     <option name="sdkName" value="Poetry (reviewsense-ecom)" />
   </component>
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12 (featurepulse-ecom)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12" project-jdk-type="Python SDK" />
 </project>
\ No newline at end of file

.idea/reviewsense-ecom.iml

@@ -2,7 +2,7 @@
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager">
     <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="Python 3.12 (featurepulse-ecom)" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="Python 3.12" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>
\ No newline at end of file

src/reviewsense_ecom/core/config.py

-
-from functools import lru_cache
-
-from pydantic.v1 import BaseSettings
-
-
-class Settings(BaseSettings):
-    """Application configuration settings"""
-    ASTRA_DB_API_ENDPOINT: str = "https://0c52512b-0c65-4e70-ac47-71edf5244a82-us-east-2.apps.astra.datastax.com"
-    ASTRA_DB_APPLICATION_TOKEN: str = "AstraCS:EvXpFFafufegdQJvhqlYxmxt:ef86b5996013b12140b69254bd554d7e8e10eb5a7137859b9c432f92a5a3b65c"
-    ASTRA_DB_NAMESPACE: str = "default_keyspace"
-    
-    # Default settings
-    EMBEDDING_MODEL: str = "sentence-transformers/all-mpnet-base-v2"
-    
-    class Config:
-        env_file = ".env"
-        env_file_encoding = "utf-8"
-        extra = "allow"  # Allow extra fields
-
-@lru_cache()
-def get_settings():
-    """
-    Cached settings retrieval to optimize performance
-    
-    Returns:
-        Settings: Configured application settings
-    """
-    return Settings()

src/reviewsense_ecom/llm/llm.py

@@ -5,7 +5,7 @@ from langchain_core.messages import BaseMessage
 from langchain_core.prompts import ChatPromptTemplate
 
 @lru_cache(maxsize=1)  # Cache only one instance (singleton behavior)
-def get_llm():
+def get_llm(groq_token: str):
     """
     Get a singleton LLM instance for the given Groq token.
 

src/reviewsense_ecom/model/productReviewsModel.py → src/reviewsense_ecom/model/FeatureSentiment.py

@@ -6,11 +6,3 @@ from bson import ObjectId
 class FeatureSentiment:
     positive: List[str] = field(default_factory=list)
     negative: List[str] = field(default_factory=list)
\ No newline at end of file
-
-@dataclass
-class ProductReview:
-    id: Optional[ObjectId] = None
-    product_id: str = ""
-    review: str = ""
-    rating: float = 0.0
-    features: List[Dict[str, FeatureSentiment]] = field(default_factory=list)
\ No newline at end of file

src/reviewsense_ecom/model/ProductReview.py

 from dataclasses import dataclass, field
-from typing import List, Dict, Optional,Any
+from typing import List, Dict, Optional, Any
 from bson import ObjectId
 from pydantic import Field
 
 
-@dataclass
-class FeatureSentiment:
-    positive: List[str] = field(default_factory=list)
-    negative: List[str] = field(default_factory=list)
-
 @dataclass
 class ProductReview:
-    #id: Optional[ObjectId] = None
+    # id: Optional[ObjectId] = None
     product_id: str = ""
     review: Optional[str] = Field(default=None, max_length=5000, description="Review text")
     rating: float = 0.0

src/reviewsense_ecom/model/ReviewResponse.py

-from typing import List, Dict, Optional
-
-from groq import BaseModel
-from src.reviewsense_ecom.model.RatingSummary import RatingSummary
-class ReviewResponse(BaseModel):
-    review_ratings: Dict[str, Optional[float]]
-    ratings_summary: RatingSummary
\ No newline at end of file

src/reviewsense_ecom/mongo/mongo_db_config.py

@@ -4,7 +4,7 @@ from pymongo import MongoClient
 from datetime import datetime, timezone
 from src.reviewsense_ecom.model.ProductReview import ProductReview
 from src.reviewsense_ecom.model.Product import Product
-from src.reviewsense_ecom.model.productReviewsModel import FeatureSentiment
+from src.reviewsense_ecom.model.FeatureSentiment import FeatureSentiment
 from dotenv import load_dotenv
 import os
 

src/reviewsense_ecom/service/retrieval.py → src/reviewsense_ecom/retriever/retrieval.py

@@ -2,7 +2,6 @@
 from functools import lru_cache
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_astradb import AstraDBVectorStore
-from src.reviewsense_ecom.core.config import get_settings
 
 
 
@@ -21,7 +20,6 @@ def get_vector_store(
     Returns:
         AstraDBVectorStore: Configured vector store instance
     """
-    settings = get_settings()
 
     # Initialize embeddings
     embeddings = HuggingFaceEmbeddings(model_name=embedding_model)

src/reviewsense_ecom/service/BotService.py

@@ -9,7 +9,7 @@ from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.prompts import ChatPromptTemplate
 
 from src.reviewsense_ecom.llm.llm import get_llm, generate_response
-from src.reviewsense_ecom.service.retrieval import get_vector_store
+from src.reviewsense_ecom.retriever.retrieval import get_vector_store
 
 
 logger = getLogger(__name__)

src/reviewsense_ecom/service/ReviewService.py

 from typing import List, Dict, Optional
 
-
 from src.reviewsense_ecom.mongo.mongo_db_config import get_db_connection
-from src.reviewsense_ecom.service.ratings_fetcher import RatingsFetcher
-from src.reviewsense_ecom.service.review_fetcher import ReviewFetcher
 from src.reviewsense_ecom.service.review_rater import ReviewRater
-from src.reviewsense_ecom.service.review_adder import ReviewAdder
 
 
 class ReviewService:
@@ -13,25 +9,18 @@ class ReviewService:
 
     def __init__(self, embedding_model="sentence-transformers/all-mpnet-base-v2"):
 
-
         """
         Initialize the review service with MongoDB connection.
         """
 
         # Vector-based processing components
         self.embedding_model = embedding_model
-        self.fetcher = ReviewFetcher()
         self.rater = ReviewRater()
-        self.adder = ReviewAdder()
-        self.ratingsFetcher = RatingsFetcher()
-
-
 
     def _get_collection(self, collection_name):
         """Returns the requested MongoDB collection."""
         return get_db_connection(collection_name)
 
-
     def get_review_by_feature(self, product_id, feature):
         """
         Fetch reviews from MongoDB based on `product_id` and `feature`
@@ -120,22 +109,5 @@ class ReviewService:
             "average_rating": average_rating
         }
 
-    # 🔹 Fetch reviews using vector-based method
-    def fetch_reviews(self, product_id: str, features: List[str], threshold: float = 0.5) -> Dict[str, List[str]]:
-        return self.fetcher.fetch_reviews(product_id, features, threshold)
-
-    # 🔹 Generate feature-specific ratings
-    def generate_feature_ratings(self, reviews_by_feature: Dict[str, List[str]]) -> Dict[str, Optional[float]]:
-        return self.rater.generate_feature_ratings(reviews_by_feature)
-
     def fetch_feature_ratings(self, reviews_by_feature: List[Dict[str, str]]) -> Dict[str, Dict[str, Optional[float]]]:
         return self.rater.generate_feature_ratings(reviews_by_feature)
-
-
-    # 🔹 Add a new review
-    def add_review(self, product_id: str, review: str, rating: int) -> str:
-        return self.adder.add_review(product_id, review, rating)
-
-    # 🔹 Fetch product ratings
-    def fetch_ratings(self, product_id: str):
-        return self.ratingsFetcher.fetch_ratings(product_id=product_id)

src/reviewsense_ecom/service/feature_extractor.py

 from pydantic import BaseModel
 from langchain.prompts import ChatPromptTemplate
 from langchain_core.output_parsers import JsonOutputParser
-from typing import List,Dict
+from typing import List, Dict
 from src.reviewsense_ecom.llm.llm import get_llm
 import re
 from dotenv import load_dotenv
@@ -10,6 +10,7 @@ import os
 # Load environment variables from .env file
 load_dotenv()
 
+
 class FeatureReviews(BaseModel):
     feature_reviews: List[dict]  # Each review will include a sentence and sentiment
 

src/reviewsense_ecom/service/ratings_fetcher.py

-# services/review_fetcher.py
-
-from typing import Dict
-from src.reviewsense_ecom.service.retrieval import get_vector_store
-from src.reviewsense_ecom.service.feature_extractor import FeatureExtractor
-from typing import (Any)
-
-
-class RatingsFetcher:
-    """Class for fetching reviews from the vector store"""
-
-    def __init__(self):
-        self.vector_store = get_vector_store()
-        self.feature_extractor = FeatureExtractor()
-
-    def fetch_ratings(self, product_id: str) -> Dict[str, Any]:
-        rating_distribution = {}
-        filter_criteria = {"title": product_id}
-        documents = self.vector_store.metadata_search(filter=filter_criteria, n=100)
-        ratings_count = len(documents)
-
-        total_rating = 0
-        rated_documents = 0
-        total_reviews = []
-
-        for doc in documents:
-            total_reviews.append(doc.page_content.lstrip("Review: "))
-            if 'rating' in doc.metadata:
-                rating = str(doc.metadata['rating'])
-                rating_distribution[rating] = rating_distribution.get(rating, 0) + 1
-                total_rating += float(rating)
-                rated_documents += 1
-
-        # Calculate average rating, handling case where there are no ratings
-        average_rating = round(total_rating / rated_documents, 2) if rated_documents > 0 else 0
-
-        return {
-            "ratings_count": ratings_count,
-            "average_rating": average_rating,
-            "rating_distribution": rating_distribution,
-            "total_reviews": total_reviews
-        }

src/reviewsense_ecom/service/review_adder.py

-# router/review_adder.py
-
-from langchain_community.docstore.document import Document
-from src.reviewsense_ecom.service.retrieval import get_vector_store
-
-
-class ReviewAdder:
-    """Class for adding reviews to the vector store"""
-
-    def __init__(self):
-        self.vector_store = get_vector_store()
-
-    def add_review(self, product_id: str, review: str, rating: int) -> str:
-        review_document = Document(page_content=review, metadata={"title": product_id, "rating": rating})
-        return self.vector_store.add_documents([review_document])[0]

src/reviewsense_ecom/service/review_fetcher.py

-# router/review_fetcher.py
-
-from typing import List, Dict
-from src.reviewsense_ecom.service.retrieval import get_vector_store
-from src.reviewsense_ecom.service.feature_extractor import FeatureExtractor
-
-
-class ReviewFetcher:
-    """Class for fetching reviews from the vector store"""
-
-    def __init__(self):
-        self.vector_store = get_vector_store()
-        self.feature_extractor = FeatureExtractor()
-
-    def fetch_reviews(self, product_id: str, features: List[str], threshold: float = 0.5) -> Dict[str, List[str]]:
-        feature_reviews = {}
-
-        for feature in features:
-            filter_criteria = {"title": product_id}
-            # documents = self.vector_store.similarity_search_with_score_id(query=self.generate_feature_query(feature), k=100, filter=filter_criteria)
-            documents = self.vector_store.similarity_search_with_score_id(query=feature, k=100, filter=filter_criteria)
-            if len(documents) != 0:
-                filtered_reviews = [doc.page_content for doc, score, _ in documents if score > threshold]
-                if len(filtered_reviews) != 0:
-                    extracted_reviews = self.feature_extractor.extract_feature_reviews(filtered_reviews, feature)
-                    if len(extracted_reviews) != 0:
-                        feature_reviews[feature] = extracted_reviews
-
-        return feature_reviews
-
-    def generate_feature_query(self, feature: str) -> str:
-        """
-        Generate semantic search query for different product features
-
-        Args:
-            feature (str): Product feature to search
-
-        Returns:
-            str: Semantic search query
-        """
-        feature_queries = {
-            "battery": "battery performance, battery life, charging speed, power consumption, battery drain, long-lasting battery",
-            "backup": "data backup, storage capacity, backup options, cloud storage, data protection, file recovery",
-            "design": "build quality, aesthetic design, material, form factor, ergonomics, look and feel, physical appearance",
-            "display": "screen quality, display resolution, color accuracy, brightness, viewing angles, screen technology, display performance"
-        }
-
-        # Default to feature name if not found
-        return feature_queries.get(feature.lower(), feature)