Update app.py

app.py

@@ -1,158 +1,100 @@
-#This app is running
 import streamlit as st
-from IPython.display import display, Markdown
 import os
 from pathlib import Path
 from llama_index.core.query_engine.router_query_engine import RouterQueryEngine
 from llama_index.core.selectors import LLMSingleSelector
 from llama_index.core.tools import QueryEngineTool
 from llama_index.core import SummaryIndex, VectorStoreIndex
-from llama_index.core import VectorStoreIndex
-from llama_index.core import Settings
-from llama_index.llms.openai import OpenAI
-#from llama_index.embeddings.openai import OpenAIEmbedding
-#from llama_index.core.node_parser import SentenceSplitter
+from llama_index.core import VectorStoreIndex, Settings
 from llama_index.core import SimpleDirectoryReader
 from llama_index.llms.groq import Groq
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-#from llama_index.embeddings.fastembed import FastEmbedEmbedding
-#from llama_index.llms.mistralai import MistralAI
-# from llama_index.embeddings.huggingface_api import (
-#     HuggingFaceInferenceAPIEmbedding,
-# )
 from typing import Tuple
 from llama_index.core import StorageContext, load_index_from_storage
 from llama_index.core.objects import ObjectIndex
 from llama_index.core.agent import ReActAgent
 
-#LOAD FROM INDEX
-async def create_doc_tools(
-    document_fp: str,
-    doc_name: str,
-    verbose: bool = True,
-) -> Tuple[QueryEngineTool]:
-    # load lora_paper.pdf documents
+# Function to process files and create document tools
+async def create_doc_tools(document_fp: str, doc_name: str, verbose: bool = True) -> Tuple[QueryEngineTool,]:
     documents = SimpleDirectoryReader(input_files=[document_fp]).load_data()
 
-    # # chunk_size of 1024 is a good default value
-    # splitter = SentenceSplitter(chunk_size=1024)
-    # # Create nodes from documents
-    # nodes = splitter.get_nodes_from_documents(documents)
-
-    # LLM model
     Settings.llm = Groq(model="mixtral-8x7b-32768")
-    # embedding model
     Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-large-en-v1.5")
-     
-    load_dir_path = f"/home/achuthchandrasekhar/Documents/AMGPT/agentic_index/{doc_name}"
 
-    # rebuild storage context
+    load_dir_path = f"/home/user/app/agentic_index/{doc_name}"
     storage_context = StorageContext.from_defaults(persist_dir=load_dir_path)
-
-    # load index
     vector_index = load_index_from_storage(storage_context)
-
- 
-    # vector query engine
     vector_query_engine = vector_index.as_query_engine()
 
-   
-
     vector_tool = QueryEngineTool.from_defaults(
         name=f"{doc_name}_vector_query_engine_tool",
         query_engine=vector_query_engine,
-        description=(
-            f"Useful for retrieving specific context from the the {doc_name}."
-        ),
+        description=f"Useful for retrieving specific context from the {doc_name}.",
     )
 
     return vector_tool
 
+# Function to find and sort .tex files
+def find_tex_files(directory: str):
+    tex_files = []
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            if file.endswith(('.tex', '.txt')):
+                file_path = os.path.abspath(os.path.join(root, file))
+                tex_files.append(file_path)
+    tex_files.sort()
+    return tex_files
+
+# Main app function
+def main():
+    st.title("PDF Question Answering with LangChain")
+
+    # API Key input
+    api_key = st.text_input("Enter your Groq API Key", type="password")
+
+    if api_key:
+        directory = '/home/user/app/rag_docs_final_review_tex_merged'
+        tex_files = find_tex_files(directory)
+
+        paper_to_tools_dict = {}
+        for paper in tex_files:
+            path = Path(paper)
+            vector_tool = await create_doc_tools(doc_name=path.stem, document_fp=path)
+            paper_to_tools_dict[path.stem] = [vector_tool]
+
+        initial_tools = [t for paper in tex_files for t in paper_to_tools_dict[Path(paper).stem]]
+
+        obj_index = ObjectIndex.from_objects(
+            initial_tools,
+            index_cls=VectorStoreIndex,
+        )
 
-# Define the directory containing the .tex files
-directory = '/home/achuthchandrasekhar/Documents/AMGPT/advanced_rag_code/rag_docs_final_review_tex_merged'
-
-# Initialize an empty list to store the file paths
-tex_files = []
-
-# Walk through the directory and find all .tex files
-for root, dirs, files in os.walk(directory):
-    for file in files:
-        if file.endswith(('.tex', '.txt')):
-            # Get the absolute path of the file
-            file_path = os.path.abspath(os.path.join(root, file))
-            tex_files.append(file_path)
-
-# Sort the list of file paths in alphabetical order
-tex_files.sort()
-
-# Create the desired output format
-output = 'tex_files = [\n'
-for file_path in tex_files:
-    output += f'    "{file_path}",\n'
-output += ']'
-
-# Print the output
-print(output)
-
-
-
-
-paper_to_tools_dict = {}
-
-
-for paper in tex_files:
-    print(f"Creating {paper} tool")
-    path = Path(paper)
-    vector_tool = await create_doc_tools(doc_name=path.stem, document_fp=path)
-    paper_to_tools_dict[path.stem] = [vector_tool]
-
-
-initial_tools = [t for paper in tex_files for t in paper_to_tools_dict[Path(paper).stem]]
-
-
-st.title("PDF Question Answering with LangChain")
+        obj_retriever = obj_index.as_retriever(similarity_top_k=6)
 
+        llm = Groq(model="mixtral-8x7b-32768")
 
-    
-# API Key input
-api_key = st.text_input("Enter your Groq API Key", type="password")
+        context = """You are an agent designed to answer scientific queries over a set of given documents.
+        Please always use the tools provided to answer a question. Do not rely on prior knowledge.
+        """
 
-if api_key:
-   
-    obj_index = ObjectIndex.from_objects(
-                initial_tools,
-                index_cls=VectorStoreIndex,
+        agent = ReActAgent.from_tools(
+            tool_retriever=obj_retriever,
+            llm=llm,
+            verbose=True,
+            context=context
         )
 
-    obj_retriever = obj_index.as_retriever(similarity_top_k=6)
-    
-    # Define LLM
-    llm = Groq(model="mixtral-8x7b-32768")
-    
-    # Add Context
-    context = """You are an agent designed to answer scientific queries over a set of given documents.
-    Please always use the tools provided to answer a question. Do not rely on prior knowledge.
-    """
-    
-    agent = ReActAgent.from_tools(
-        tool_retriever=obj_retriever,
-        llm=llm,
-        verbose=True,
-        context=context
-    )
-            
-
-    # User prompt input
-    user_prompt = st.text_input("Enter your question")
-    
-    if user_prompt:
-        with st.spinner("Processing..."):
-            response = agent.query(user_prompt)
-            markdown_response = f"""
+        user_prompt = st.text_input("Enter your question")
+
+        if user_prompt:
+            with st.spinner("Processing..."):
+                response = agent.query(user_prompt)
+                markdown_response = f"""
                     ### Query Response:
                     
                     {response}
-                    """
-            st.write(markdown_response)
+                """
+                st.write(markdown_response)
 
+if __name__ == "__main__":
+    main()