Create app.py

app.py

@@ -0,0 +1,98 @@
+
+import subprocess
+import gradio as gr
+
+subprocess.call(["pip ","-q","install", "sentence-transformers"])
+subprocess.call(["pip","install","langchain"])
+# Install pypdf
+subprocess.call(["pip", "install", "-q", "pypdf"])
+
+# Install python-dotenv
+subprocess.call(["pip", "install", "-q", "python-dotenv"])
+
+# Install transformers
+subprocess.call(["pip", "install", "-q", "transformers"])
+
+# Install llama-cpp-python with specific CMAKE_ARGS
+subprocess.call(["pip", "install", "llama-cpp-python", "--no-cache-dir", "--install-option", "--CMAKE_ARGS=-DLLAMA_CUBLAS=on", "--install-option", "--FORCE_CMAKE=1"])
+
+# Install llama-index
+subprocess.call(["pip", "install", "-q", "llama-index"])
+
+
+
+import logging
+import sys
+
+logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
+
+from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
+
+
+documents = SimpleDirectoryReader("/content/Data/").load_data()
+
+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,
+)
+
+
+
+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")
+)
+
+
+service_context = ServiceContext.from_defaults(
+    chunk_size=256,
+    llm=llm,
+    embed_model=embed_model
+)
+
+index = VectorStoreIndex.from_documents(documents, service_context=service_context)
+
+query_engine = index.as_query_engine()
+
+def query_handler(query):
+    response = query_engine.query(query)
+    return response
+
+# Create an interface with a text input for user query
+iface = gr.Interface(
+    fn=query_handler,
+    inputs=gr.Textbox(prompt="Enter your question here..."),
+    outputs=gr.Textbox(),
+    live=True,
+    capture_session=True,
+    interpretation="query",
+)
+
+# Launch the interface
+iface.launch()
+
+