Update app.py

app.py

@@ -2,9 +2,9 @@ import os
 import requests
 import tellurium as te
 import tempfile
+import ollama
 import streamlit as st
 from langchain_text_splitters import CharacterTextSplitter
-from transformers import pipeline
 import chromadb
 
 # Constants and global variables
@@ -16,10 +16,6 @@ LOCAL_DOWNLOAD_DIR = tempfile.mkdtemp()
 cached_data = None
 db = None
 
-# Initialize Hugging Face model pipelines
-summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
-llm = pipeline("text-generation", model="gpt2")
-
 def fetch_github_json():
     url = f"https://api.github.com/repos/{GITHUB_OWNER}/{GITHUB_REPO_CACHE}/contents/{BIOMODELS_JSON_DB_PATH}"
     headers = {"Accept": "application/vnd.github+json"}
@@ -144,15 +140,20 @@ def create_vector_db(final_items):
         metadata={"hnsw:space": "cosine"}
     )
     documents = []
-    print("VectorDB successfully created.")
+    
     for item in final_items:
         prompt = f"""
-        Summarize the following segment of Antimony:
-        {item}
+        Summarize the following segment of Antimony in a clear and concise manner:
+        1. Provide a detailed summary using a limited number of words
+        2. Maintain all original values and include any mathematical expressions or values in full. 
+        3. Ensure that all variable names and their values are clearly presented. 
+        4. Write the summary in paragraph format, putting an emphasis on clarity and completeness. 
+        
+        Here is the antimony segment to summarize: {item}
         """
-        response = summarizer(prompt, max_length=150, min_length=30, do_sample=False)
-        summary = response[0]['summary_text']
-        documents.append(summary)
+        documents5 = ollama.generate(model="llama3", prompt=prompt)
+        documents2 = documents5['response']
+        documents.append(documents2)
     
     if final_items:
         db.add(
@@ -170,14 +171,25 @@ def generate_response(db, query_text, previous_context):
     if not query_results.get('documents'):
         return "No results found."
     
-    best_recommendation = query_results['documents'][0]
+    best_recommendation = query_results['documents']
     
     prompt_template = f"""
-    Using the context below, answer the following question: {query_text}
-    Context: {previous_context} {best_recommendation}
+    Using the context provided below, answer the following question. If the information is insufficient to answer the question, please state that clearly. 
+    
+    Context:
+    {previous_context} {best_recommendation}
+    
+    Instructions:
+    1. Cross-Reference: Use all provided context to define variables and identify any unknown entities. 
+    2. Mathematical Calculations: Perform any necessary calculations based on the context and available data. 
+    3. Consistency: Remember and incorporate previous responses if the question is related to earlier information. 
+    
+    Question: 
+    {query_text}
+
     """
-    response = llm(prompt_template, max_length=150)
-    final_response = response[0]['generated_text']
+    response = ollama.generate(model="llama3", prompt=prompt_template)
+    final_response = response.get('response', 'No response generated')
     return final_response
 
 def streamlit_app():