Create app.py

app.py

@@ -0,0 +1,158 @@
+#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 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
+    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
+    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}."
+        ),
+    )
+
+    return vector_tool
+
+
+# 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")
+
+
+    
+# API Key input
+api_key = st.text_input("Enter your Groq API Key", type="password")
+
+if api_key:
+   
+    obj_index = ObjectIndex.from_objects(
+                initial_tools,
+                index_cls=VectorStoreIndex,
+        )
+
+    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"""
+                    ### Query Response:
+                    
+                    {response}
+                    """
+            st.write(markdown_response)
+