{ 
"original_query": "...",
 "corrected_query": "...",
 "translation": "..."
}

!pip install -q pandas langchain langchain-core langchain-groq langchain-chroma fastembed langchain-community

import pandas as pd
from io import StringIO
csv_data = """product_id,product_name,category,tags
1,Aashirvaad Select Atta 5kg,Staples,"atta, flour, gehu, aata, wheat"
2,Amul Gold Milk 1L,Dairy,"milk, doodh, paal, full cream milk"
3,Tata Salt 1kg,Staples,"salt, namak, uppu"
4,Kellogg's Corn Flakes 475g,Breakfast,"cornflakes, breakfast cereal, makkai"
5,Parle-G Gold Biscuit 1kg,Snacks,"biscuit, cookies, biscuits"
6,Cadbury Dairy Milk Silk,Chocolates,"chocolate, choco, silk, dairy milk"
7,Haldiram's Classic Banana Chips,Snacks,"kele chips, banana wafers, chips"
8,MDH Deggi Mirch Masala,Spices,"mirchi, masala, spice, red chili powder"
9,Fresh Coriander Bunch (Dhaniya),Vegetables,"coriander, dhaniya, kothimbir, cilantro"
10,Fresh Mint Leaves Bunch (Pudina),Vegetables,"mint, pudhina, pudina patta"
11,Taj Mahal Red Label Tea 500g,Beverages,"tea, chai, chaha, red label"
12,Nescafe Classic Coffee 100g,Beverages,"coffee, koffee, nescafe"
13,Onion 1kg (Kanda),Vegetables,"onion, kanda, pyaz"
14,Tomato 1kg,Vegetables,"tomato, tamatar"
15,Coca-Cola Original Taste 750ml,Beverages,"coke, coca-cola, soft drink, cold drink"
16,Maggi 2-Minute Noodles Masala,Snacks,"maggi, noodles, instant food"
17,Amul Cheese Slices 100g,Dairy,"cheese, cheese slice, paneer slice"
18,Britannia Cheese Spread 180g,Dairy,"cheese, cheese spread, creamy cheese"
19,Fresh Lemon 4pcs (Nimbu),Vegetables,"lemon, nimbu, lime"
20,Saffola Gold Edible Oil 1L,Staples,"oil, tel, cooking oil, saffola"
21,Basmati Rice 1kg,Staples,"rice, chawal, basmati"
22,Kurkure Masala Munch,Snacks,"kurkure, snacks, chips"
"""
df = pd.read_csv(StringIO(csv_data))
print("Product Catalog successfully loaded.")
df.head()

import os
import json
from langchain.schema import Document
from langchain.embeddings import FastEmbedEmbeddings
from langchain_chroma import Chroma
# Create LangChain Documents
documents = [
 Document(
 page_cnotallow=f"{row['product_name']}. Category: {row['category']}. Tags: {row['tags']}",
 metadata={
 "product_id": row['product_id'],
 "product_name": row['product_name'],
 "category": row['category']
 }
 ) for _, row in df.iterrows()
]
# Initialize embedding model and vector store
embedding_model = FastEmbedEmbeddings(model_name="BAAI/bge-small-en-v1.5")
vectorstore = Chroma.from_documents(documents, embedding_model)
# The retriever will be used to fetch the top-k most similar documents
retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
print("Vector database initialized and retriever is ready.")

from langchain_groq import ChatGroq
from langchain_core.prompts import ChatPromptTemplate
# IMPORTANT: Set your Groq API key here or as an environment variable
os.environ["GROQ_API_KEY"] = "YOUR_API_KEY” # Replace with your key
llm = ChatGroq(
 temperature=0,
 model_name="llama3-8b-8192",
 model_kwargs={"response_format": {"type": "json_object"}},
)
prompt_template = """
You are a world-class search query interpretation engine for a grocery delivery service like Zepto.
Your primary goal is to understand the user's *intent*, even if their query is misspelled, in a different language, or uses slang.
Analyze the user's `RAW QUERY` and the `CONTEXT` of semantically similar products retrieved from our catalog.
Based on this, determine the most likely product the user is searching for.
**INSTRUCTIONS:**
1. Compare the `RAW QUERY` against the product names in the `CONTEXT`.
2. Identify the single best match from the `CONTEXT`.
3. Generate a clean, corrected search query for that product.
4. Provide a confidence score (High, Medium, Low) and a brief reasoning for your choice.
5. Return a single JSON object with the following schema:
 - "corrected_query": A clean, corrected search term.
 - "identified_product": The full name of the single most likely product from the context.
 - "confidence": Your confidence in the decision: "High", "Medium", or "Low".
 - "reasoning": A brief, one-sentence explanation of why you made this choice.
If the query is too ambiguous or has no good match in the context, confidence should be "Low" and `identified_product` can be `null`.
---
CONTEXT:
{context}
RAW QUERY:
{query}
---
JSON OUTPUT:
"""
prompt = ChatPromptTemplate.from_template(prompt_template)
print("LLM and Prompt Template are configured.")

from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
def format_docs(docs):
 """Formats the retrieved documents for the prompt."""
 return "\n".join([f"- {d.metadata['product_name']}" for d in docs])
# The main RAG chain
rag_chain = (
 {"context": retriever | format_docs, "query": RunnablePassthrough()}
 | prompt
 | llm
 | StrOutputParser()
)
def search_pipeline(query: str):
 """Executes the full search and correction pipeline."""
 print(f"\n{'='*50}")
 print(f"Executing Pipeline for Query: '{query}'")
 print(f"{'='*50}")
 # --- Stage 1: Semantic Retrieval ---
 initial_context = retriever.get_relevant_documents(query)
 print("\n[Stage 1: Semantic Retrieval]")
 print("Found the following products for context:")
 for doc in initial_context:
 print(f" - {doc.metadata['product_name']}")
 # --- Stage 2: LLM Correction & Selection ---
 print("\n[Stage 2: LLM Correction & Selection]")
 llm_output_str = rag_chain.invoke(query)
 try:
 llm_output = json.loads(llm_output_str)
 print("LLM successfully parsed the query and returned:")
 print(json.dumps(llm_output, indent=2))
 corrected_query = llm_output.get('corrected_query', query)
 except (json.JSONDecodeError, AttributeError) as e:
 print(f"LLM output failed to parse. Error: {e}")
 print(f"Raw LLM output: {llm_output_str}")
 corrected_query = query # Fallback to original query
 # --- Final Step: Search with Corrected Query ---
 print("\n[Final Step: Search with Corrected Query]")
 print(f"Searching for the corrected term: '{corrected_query}'")
 final_results = vectorstore.similarity_search(corrected_query, k=3)
 print("\nTop 3 Product Results:")
 for i, doc in enumerate(final_results):
 print(f" {i+1}. {doc.metadata['product_name']} (ID: {doc.metadata['product_id']})")
 print(f"{'='*50}\n")
print("End-to-end search pipeline is ready.")

# --- Test Case 1: Simple Misspelling ---
search_pipeline("aata")
# --- Test Case 2: Vernacular Term ---
search_pipeline("kanda")
# --- Test Case 3: Brand Name + Misspelling ---
search_pipeline("cococola")
# --- Test Case 4: Ambiguous Query ---
search_pipeline("chese")
# --- Test Case 5: Highly Ambiguous / Vague Query ---
search_pipeline("drink")