Upload 5 files

README.md

@@ -0,0 +1,10 @@
+---
+title: Cinco Return Chatbot
+emoji: 🤖
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: "3.50.2"
+app_file: app.py
+pinned: false
+---

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline
+
+# Load a lightweight, CPU-friendly model
+model_id = "google/flan-t5-base"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
+
+# Pipeline setup
+chatbot = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
+
+# Function to format prompt for chat-like interaction
+def format_prompt(user_input):
+    base_prompt = (
+        "You are Cinco, a helpful assistant that answers customer questions ONLY about product returns, refunds, and exchanges.\n"
+        "Respond concisely, clearly, and don't repeat the question. If the question is not about returns, politely say so.\n\n"
+        f"Customer: {user_input}\n"
+        f"Cinco Assistant:"
+    )
+    
+# Chatbot logic
+def chat_fn(user_input, history):
+    history = history or []
+    prompt = format_prompt(history, user_input)
+    response = chatbot(prompt, max_length=256, do_sample=False, clean_up_tokenization_spaces=True)[0]["generated_text"]
+
+    # Extract only the latest assistant response
+    if "Cinco Assistant:" in response:
+        assistant_reply = response.split("Cinco Assistant:")[-1].strip()
+    else:
+        assistant_reply = response.strip()
+
+    history.append((user_input, assistant_reply))
+    return "", history
+
+# Build Gradio UI
+with gr.Blocks(title="Cinco Returns Chatbot") as demo:
+    gr.Markdown("## 🧾 Cinco Returns Chatbot\nAsk anything about returns, refunds, or exchanges.")
+    chatbot_ui = gr.Chatbot(label="Cinco Assistant", show_label=True)
+    with gr.Row():
+        user_input = gr.Textbox(placeholder="Example: Can I return a used item without a receipt?", scale=6)
+        submit_btn = gr.Button("Send", scale=1)
+
+    state = gr.State([])
+
+    submit_btn.click(fn=chat_fn, inputs=[user_input, state], outputs=[user_input, chatbot_ui])
+    user_input.submit(fn=chat_fn, inputs=[user_input, state], outputs=[user_input, chatbot_ui])
+
+if __name__ == "__main__":
+    demo.launch()

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

rag_utils.py

@@ -0,0 +1,32 @@
+import json
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+
+class RAGEngine:
+    def __init__(self, json_path):
+        self.embedder = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+        with open(json_path, 'r') as f:
+            self.data = json.load(f)
+        self.texts = []
+        self.build_corpus()
+        self.build_index()
+
+    def build_corpus(self):
+        # Combine multiple fields for better context
+        self.texts = [
+            f"Product: {item['product_name']}\nCategory: {item['category']}\nPolicy: {item['return_policy']}\nReason: {item['return_reason']}"
+            for item in self.data
+        ]
+
+    def build_index(self):
+        embeddings = self.embedder.encode(self.texts, convert_to_numpy=True)
+        dim = embeddings.shape[1]
+        self.index = faiss.IndexFlatL2(dim)
+        self.index.add(embeddings)
+
+    def retrieve(self, query, top_k=3):
+        query_emb = self.embedder.encode([query], convert_to_numpy=True)
+        distances, indices = self.index.search(query_emb, top_k)
+        results = [self.texts[idx] for idx in indices[0] if idx != -1]
+        return results

requirements.txt

@@ -0,0 +1,6 @@
+transformers==4.40.0
+gradio==4.44.1
+torch
+faiss-cpu
+sentence-transformers
+accelerate>=0.26.0