Update app.py

app.py

@@ -1,64 +1,42 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+import torch
+from sentence_transformers import SentenceTransformer, util
+
+model = SentenceTransformer("all-MiniLM-L6-v2")
+supply_demand_text = """
+Supply refers to the quantity of a good or service that a producer is willing and able to offer for sale at various prices.
+Demand refers to how much of a product consumers are willing and able to purchase at different prices.
+When supply exceeds demand, there is a surplus.
+When demand exceeds supply, there is a shortage.
+Equilibrium is the point where supply equals demand.
+Price acts as a signal for both producers and consumers.
+Market dynamics are influenced by shifts in supply and demand.
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+cleaned_text = supply_demand_text.strip()
+chunks = cleaned_text.split("\n")
+cleaned_chunks = []
+for chunk in chunks:
+    stripped_chunk = chunk.strip()
+    if stripped_chunk:
+        cleaned_chunks.append(stripped_chunk)
+
+chunk_embeddings = model.encode(cleaned_chunks, convert_to_tensor=True)
+
+def get_top_chunks(query):
+    query_embedding = model.encode(query, convert_to_tensor=True)
+    query_embedding = query_embedding / query_embedding.norm()
+    normalized_chunks = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)
+    similarities = torch.matmul(normalized_chunks, query_embedding)
+    top_indices = torch.topk(similarities, k=3).indices
+    top_chunks = [cleaned_chunks[i] for i in top_indices]
+    return top_chunks
+
+def chatbot_response(message, history):
+    top_chunks = get_top_chunks(message)
+    numbered_response = "\n".join([f"{i+1}. {chunk}" for i, chunk in enumerate(top_chunks)])
+    history = history or []
+    history.append((message, numbered_response))
+    return numbered_response, history
+
+chatbot = gr.ChatInterface(fn=chatbot_response, title="RAG Chatbot")
+chatbot.launch()