adding basic code

app.py

@@ -4,6 +4,73 @@ import torch
 import numpy as np
 import random
 from huggingface_hub import InferenceClient
+
+#LLM we are using
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", provider='hf-inference')
 
+#adding text file
+with open("be_a_better_you.txt", "r", encoding="utf-8") as file:
+  wellness_text = file.read()
+
+#cleaning up the text
+cleaned_text = wellness_text.strip()
+chunks = cleaned_text.split("\n")
+cleaned_chunks = []
+
+#putting text in chunks
+for chunk in chunks:
+  stripped_chunk = chunk.strip()
+  if stripped_chunk:
+    cleaned_chunks.append(stripped_chunk)
+
+#import model for embeddings
 model = SentenceTransformer('all-MiniLM-L6-v2')
+
+chunk_embeddings = model.encode(cleaned_chunks, convert_to_tensor=True)
+
+def get_top_chunks(query):
+  # creating a function taking query as my parameter
+  query_embedding = model.encode(query, convert_to_tensor=True)
+  # encode query to vector embedding for comparison
+  query_embedding_normalized = query_embedding / query_embedding.norm()
+  # normalize query to 1: allows for comparison of meaning
+  chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)
+  # normalizing chunks for comparison of meaning
+ similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized)
+  print(similarities)
+  # using matmul (matrix multiplication) method to compare query to chunks
+
+  top_indices = torch.topk(similarities, k=3).indices
+  print(top_indices)
+  # get the indices of the chunks thart are most similar to my query
+
+  top_chunks = []
+
+  for i in top_indices:
+    chunk = chunks[i]
+    # for each index number in top_indices, get back the text
+    top_chunks.append(chunk)
+
+  return top_chunks
+
+def respond(message, history):
+    messages = [{"role": "system", "content": "You are a big sister chatbot named, Nessie. You help people feel better about their bodies and self-image."}] 
+    # change the personality
+    context = get_top_chunks(message)
+   if history:
+        messages.extend(history)
+    messages.append({"role": "user", "content": message})
+
+response = ""
+    for messages in client.chat_completion(
+        messages,
+        max_tokens = 500,
+        stream = True,
+    ):
+        token = messages.choices[0].delta.content
+        response+= token 
+        yield response
+    
+chatbot = gr.ChatInterface(respond, type = "messages")
+chatbot.launch(debug=True)
+