Update app.py

app.py

@@ -1,74 +1,65 @@
-
-import subprocess
-subprocess.run(["/usr/local/bin/python", "-m", "pip", "install", "--upgrade", "sentence-transformers"])
-subprocess.run(["pip", "install", "sentence-transformers"])
-subprocess.run(["pip", "install", "langchain"])
-subprocess.run(["pip", "install", "-q", "pypdf"])
-subprocess.run(["pip", "install", "-q", "python-dotenv"])
-subprocess.run(["pip", "install", "-q", "transformers"])
-subprocess.run(["pip", "install", "llama-cpp-python", "--no-cache-dir", "--install-option", "--CMAKE_ARGS=-DLLAMA_CUBLAS=on", "--install-option", "--FORCE_CMAKE=1"])
-subprocess.run(["pip", "install", "-q", "llama-index"])
-import subprocess
-import gradio as gr
 import logging
 import sys
-from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
-from llama_index.llms import LlamaCPP
-from llama_index.llms.llama_utils import messages_to_prompt, completion_to_prompt
-from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-from llama_index.embeddings import LangchainEmbedding
 
-# Set up logging
 logging.basicConfig(stream=sys.stdout, level=logging.INFO)
 logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
 
-# Load documents
+from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
+
+
 documents = SimpleDirectoryReader("/content/Data/").load_data()
 
-# Set up LlamaCPP
+import torch
+
+from llama_index.llms import LlamaCPP
+from llama_index.llms.llama_utils import messages_to_prompt, completion_to_prompt
 llm = LlamaCPP(
+    # You can pass in the URL to a GGML model to download it automatically
     model_url='https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf',
+    # optionally, you can set the path to a pre-downloaded model instead of model_url
     model_path=None,
     temperature=0.1,
     max_new_tokens=256,
+    # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
     context_window=3900,
+    # kwargs to pass to __call__()
     generate_kwargs={},
+    # kwargs to pass to __init__()
+    # set to at least 1 to use GPU
     model_kwargs={"n_gpu_layers": -1},
+    # transform inputs into Llama2 format
     messages_to_prompt=messages_to_prompt,
     completion_to_prompt=completion_to_prompt,
     verbose=True,
 )
 
-# Set up embeddings
+
+
+
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+from llama_index.embeddings import LangchainEmbedding
+from llama_index import ServiceContext
+
 embed_model = LangchainEmbedding(
-    HuggingFaceEmbeddings(model_name="thenlper/gte-large")
+  HuggingFaceEmbeddings(model_name="thenlper/gte-large")
 )
 
-# Set up service context
+
 service_context = ServiceContext.from_defaults(
     chunk_size=256,
     llm=llm,
     embed_model=embed_model
 )
 
-# Create index
 index = VectorStoreIndex.from_documents(documents, service_context=service_context)
+
 query_engine = index.as_query_engine()
+#response = query_engine.query("What is Fibromyalgia?")
 
-# Define query handler
-def query_handler(query):
-    response = query_engine.query(query)
-    return response
-
-# Create Gradio interface
-iface = gr.Interface(
-    fn=query_handler,
-    inputs=gr.Textbox(prompt="Enter your question here..."),
-    outputs=gr.Textbox(),
-    live=True,
-    capture_session=True,
-    interpretation="query",
-)
+import gradio as gr
+
+def text_to_uppercase(text):
+    return query_engine.query(text)
 
-# Launch the interface
-iface.launch()
+iface = gr.Interface(fn=text_to_uppercase, inputs="text", outputs="text")
+iface.launch(share=True)