Update app.py

app.py

@@ -1,63 +1,154 @@
 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
-"""
-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)",
-        ),
-    ],
-)
+import os
+from pathlib import Path
+from llama_index.core.selectors import LLMSingleSelector
+from llama_index.core.tools import QueryEngineTool
+from llama_index.core import VectorStoreIndex
+from llama_index.core import Settings
+from llama_index.core import SimpleDirectoryReader
+from llama_index.llms.groq import Groq
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+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
+import sys
+import io
 
+# Function to process files and create document tools
+def create_doc_tools(document_fp: str, doc_name: str, verbose: bool = True) -> Tuple[QueryEngineTool,]:
+    documents = SimpleDirectoryReader(input_files=[document_fp]).load_data()
+
+    Settings.llm = Groq(model="mixtral-8x7b-32768")
+    Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-large-en-v1.5")
+
+    load_dir_path = f"/home/user/app/agentic_index/{doc_name}"
+    storage_context = StorageContext.from_defaults(persist_dir=load_dir_path)
+    vector_index = load_index_from_storage(storage_context)
+    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 {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
+
+def initialize_agent(apikey):
+    os.environ["GROQ_API_KEY"] = apikey
+
+    llm = Groq(model="mixtral-8x7b-32768")
+
+    try:
+        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 = 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,
+        )
+    
+        obj_retriever = obj_index.as_retriever(similarity_top_k=6)
+    
+        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
+        )
+        return agent
+    except Exception as e:
+        return str(e)
+
+def chat_with_agent(prompt, agent, verbose_toggle):
+    try:
+        # Redirect stdout
+        original_stdout = sys.stdout
+        sys.stdout = io.StringIO()
+
+        # query the agent
+        response = agent.query(prompt)
+
+        # Get the captured output and restore stdout
+        output = sys.stdout.getvalue()
+        sys.stdout = original_stdout
+
+        # format the received verbose output
+        verbose = ''
+        for output_string in output.split('==='):
+            verbose += output_string
+            verbose += '\n'
+
+        # assistant response
+        msg = f'{verbose}' if verbose_toggle else f'{response.response[10:]}'
+        
+        return msg
+    except Exception as e:
+        return str(e)
+
+# Gradio Interface
+def main():
+    # Initialize agent on startup
+    agent = None
+
+    def set_apikey(apikey):
+        nonlocal agent
+        agent = initialize_agent(apikey)
+        return "API Key Set. You may start asking questions now."
+
+    def reset_chat():
+        return "Chat reset. You may start asking questions now."
+
+    def chat_function(prompt, apikey, verbose_toggle):
+        if not agent:
+            set_apikey(apikey)
+        return chat_with_agent(prompt, agent, verbose_toggle)
+
+    with gr.Blocks() as demo:
+        gr.Markdown("# AMGPT, Powered by LlamaIndex")
+
+        with gr.Row():
+            apikey = gr.Textbox(label="Enter your Groq API Key", type="password")
+            set_apikey_button = gr.Button("Set API Key")
+        
+        set_apikey_button.click(set_apikey, inputs=apikey, outputs=None)
+
+        with gr.Row():
+            verbose_toggle = gr.Checkbox(label="Verbose", value=True)
+            reset = gr.Button("Reset Chat")
+        
+        reset.click(reset_chat, outputs=None)
+
+        prompt = gr.Textbox(label="Ask a question")
+        output = gr.Textbox(label="Response")
+
+        prompt.submit(chat_function, inputs=[prompt, apikey, verbose_toggle], outputs=output)
+
+    demo.launch()
 
 if __name__ == "__main__":
-    demo.launch()
+    main()