Create app.py

app.py

@@ -0,0 +1,96 @@
+import gradio as gr
+import openai
+import pinecone
+from textblob import TextBlob
+from langdetect import detect
+
+# Initialize OpenAI API
+openai.api_key = "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"  # Replace with your OpenAI API key
+
+# Initialize Pinecone
+pinecone.init(api_key="2c47d51e-211b-4611-8808-5510e07d1f94", environment="us-east-1")
+
+# Assume you have already created and populated an index
+index_name = "zepto"
+index = pinecone.Index(index_name)
+
+def get_embedding(text, model="text-embedding-ada-002"):
+    response = openai.Embedding.create(input=[text], model=model)
+    return response['data'][0]['embedding']
+
+def check_and_correct_spelling(query):
+    blob = TextBlob(query)
+    corrected_query = str(blob.correct())
+    return corrected_query
+
+def correct_and_complete_query(text):
+    blob = TextBlob(text)
+    corrected_text = str(blob.correct())
+    
+    completion_prompt = f"Complete the following query in a way that is related to product search: '{corrected_text}'"
+    response = openai.Completion.create(
+        model="gpt-3.5-turbo-instruct",
+        prompt=completion_prompt,
+        max_tokens=100,
+        temperature=0.5
+    )
+    
+    return response.choices[0].text.strip()
+
+def translate_to_english(text):
+    if detect(text) != 'en':
+        translation_prompt = f"Translate the following text to English:\n\n'{text}'"
+        response = openai.Completion.create(
+            model="gpt-3.5-turbo-instruct",
+            prompt=translation_prompt,
+            max_tokens=100,
+            temperature=0.5
+        )
+        return response.choices[0].text.strip()
+    return text
+
+def is_query_relevant(query, relevant_keywords=["product", "buy", "purchase"]):
+    for keyword in relevant_keywords:
+        if keyword.lower() in query.lower():
+            return True
+    return False
+
+def process_query(query):
+    query = check_and_correct_spelling(query)
+    query = correct_and_complete_query(query)
+    query = translate_to_english(query)
+    
+    if not is_query_relevant(query):
+        return "The query is not relevant. Please enter a different query."
+    
+    return query 
+
+def search_in_pinecone(query):
+    processed_query = process_query(query)
+    if processed_query.startswith("The query is not relevant"):
+        return processed_query
+    
+    embedding = get_embedding(processed_query)
+    search_results = index.query(vector=embedding, top_k=5, include_metadata=True)
+
+    result_strings = []
+    for result in search_results['matches']:
+        product_name = result['metadata'].get('product_name', 'No name available')
+        product_link = result['metadata'].get('product_url', 'No link available')
+        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)
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=search_in_pinecone,
+    inputs=gr.Textbox(label="Enter your query"),
+    outputs=gr.Textbox(label="Top 5 Similar Products"),
+    title="Product Similarity Search",
+    description="Enter a query to find the top 5 similar products based on your search."
+)
+
+# Launch the interface
+interface.launch()