Update app.py

app.py

@@ -2,70 +2,15 @@ import pandas as pd
 import numpy as np
 import torch
 from textblob import TextBlob
-data = pd.read_csv("flipkart_com-ecommerce_sample.csv")
-MAX_TEXT_LENGTH = 1000  
-def auto_truncate(val):
-    """Truncate the given text."""
-    return val[:MAX_TEXT_LENGTH] if isinstance(val, str) else val
-all_prods_df = pd.read_csv("flipkart_com-ecommerce_sample.csv", converters={
-    'description': auto_truncate,
-    'product_specifications': auto_truncate,
-    'product_name': auto_truncate,
-    'product_category_tree': auto_truncate,
-})
-
-all_prods_df['product_specifications'].replace('', None, inplace=True)
-all_prods_df.dropna(subset=['product_specifications'], inplace=True)
-
-all_prods_df.reset_index(drop=True, inplace=True)
-NUMBER_PRODUCTS = 16000
-
-product_metadata = (
-    all_prods_df
-    .head(NUMBER_PRODUCTS)
-    .to_dict(orient='index')
-)
-texts = [
-    v['product_name'] for k, v in product_metadata.items()
-]
-
-metadatas = list(product_metadata.values())
 import openai
+import gradio as gr
+from pinecone import Pinecone
+from langdetect import detect
+
 openai.api_key = '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'
+pc = Pinecone(api_key="2c47d51e-211b-4611-8808-5510e07d1f94")
 def get_embedding(text, model="text-embedding-ada-002"):
     return openai.embeddings.create(input=[text], model=model).data[0].embedding
-
-embeddings = [get_embedding(text) for text in texts]
-from pinecone import Pinecone
-pc = Pinecone(api_key="2c47d51e-211b-4611-8808-5510e07d1f94", environment="us-east-1")
-index = pc.Index('zepto')
-vectors = []
-for i, (embedding, metadata) in enumerate(zip(embeddings, metadatas)):
-    vectors.append({
-        'id': str(i),  
-        'values': embedding,  
-        'metadata': {
-            'product_name': metadata.get('product_name', 'No name available'),
-            'product_url': metadata.get('product_url', 'No link available')
-        }
-    })
-import math
-
-def batch_upsert(index, vectors, batch_size=100):
-    """Upsert vectors to Pinecone in batches."""
-    num_batches = math.ceil(len(vectors) / batch_size)
-
-    for i in range(num_batches):
-        batch_start = i * batch_size
-        batch_end = batch_start + batch_size
-        batch_vectors = vectors[batch_start:batch_end]
-
-        index.upsert(vectors=batch_vectors)
-        print(f"Upserted batch {i + 1}/{num_batches}")
-
-batch_size = 50  
-batch_upsert(index, vectors, batch_size=batch_size)
-from langdetect import detect
 def check_and_correct_spelling(query):
     blob = TextBlob(query)
     corrected_query = str(blob.correct())
@@ -100,22 +45,18 @@ def is_query_relevant(query, relevant_keywords):
         if keyword.lower() in query.lower():
             return True
     return False
-def search_in_pinecone(query):
-    embedding = get_embedding(query)
-    search_result = index.query(vector=embedding, top_k=5, include_metadata=True)
-    return search_result
 def process_query(query):
     query = check_and_correct_spelling(query)
-    
+
     query = correct_and_complete_query(query)
-    
+
     query = translate_to_english(query)
-    
+
     # Step 4: Check if the query is relevant
     # if not is_query_relevant(query):
     #     return "The query is not relevant. Please enter a different query."
-    
-    return query 
+
+    return query
 def search_in_pinecone2(query):
     processed_query = process_query(query)
     embedding = get_embedding(query)
@@ -128,9 +69,9 @@ def search_in_pinecone2(query):
         score = result['score']
         result_string = f"Product: {product_name}\nLink: {product_link}\nScore: {score}\n"
         result_strings.append(result_string)
-    
+
     return "\n".join(result_strings)
-import gradio as gr
+index = pc.Index('quickstart')
 interface = gr.Interface(
     fn=search_in_pinecone2,
     inputs=gr.Textbox(label="Enter your query"),