Spaces:
Sleeping
Sleeping
File size: 3,458 Bytes
5ca6388 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
import os
import gradio as gr
from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
from llama_index.embeddings.mixedbreadai import MixedbreadAIEmbedding
from llama_index.llms.groq import Groq
from llama_parse import LlamaParse
# API keys
llama_cloud_key = os.environ.get("LLAMA_CLOUD_API_KEY")
groq_key = os.environ.get("GROQ_API_KEY")
mxbai_key = os.environ.get("MXBAI_API_KEY")
if not (llama_cloud_key and groq_key and mxbai_key):
raise ValueError(
"API Keys not found! Ensure they are passed to the Docker container."
)
# models name
llm_model_name = "llama-3.1-70b-versatile"
embed_model_name = "mixedbread-ai/mxbai-embed-large-v1"
# Initialize the parser
parser = LlamaParse(api_key=llama_cloud_key, result_type="markdown")
# Define file extractor with various common extensions
file_extractor = {
".pdf": parser,
".docx": parser,
".doc": parser,
".txt": parser,
".csv": parser,
".xlsx": parser,
".pptx": parser,
".html": parser,
".jpg": parser,
".jpeg": parser,
".png": parser,
".webp": parser,
".svg": parser,
}
# Initialize the embedding model
embed_model = MixedbreadAIEmbedding(api_key=mxbai_key, model_name=embed_model_name)
# Initialize the LLM
llm = Groq(model="llama-3.1-70b-versatile", api_key=groq_key)
# File processing function
def load_files(file_path: str):
global vector_index
document = SimpleDirectoryReader(
input_files=[file_path], file_extractor=file_extractor
).load_data()
vector_index = VectorStoreIndex.from_documents(document, embed_model=embed_model)
print(f"Parsing done for {file_path}")
filename = os.path.basename(file_path)
return f"Ready to provide responses based on {filename}"
# Respond function
def respond(message, history):
# Use the preloaded LLM
query_engine = vector_index.as_chat_engine(llm=llm)
streaming_response = query_engine.stream_chat(message)
partial_text = ""
for new_text in streaming_response.response_gen:
partial_text += new_text
# Yield an empty string to cleanup the message textbox and the updated conversation history
yield partial_text
# UI Setup
with gr.Blocks(
theme=gr.themes.Default(
primary_hue="green",
secondary_hue="blue",
font=[gr.themes.GoogleFont("Poppins")],
),
css="footer {visibility: hidden}",
) as demo:
gr.Markdown("# DataCamp Doc Q&A 🤖📃")
with gr.Row():
with gr.Column(scale=1):
file_input = gr.File(
file_count="single", type="filepath", label="Upload Document"
)
with gr.Row():
btn = gr.Button("Submit", variant="primary")
clear = gr.Button("Clear")
output = gr.Textbox(label="Status")
with gr.Column(scale=3):
chatbot = gr.ChatInterface(
fn=respond,
chatbot=gr.Chatbot(height=300),
theme="soft",
show_progress="full",
textbox=gr.Textbox(
placeholder="Ask questions about the uploaded document!",
container=False,
),
)
# Set up Gradio interactions
btn.click(fn=load_files, inputs=file_input, outputs=output)
clear.click(
lambda: [None, None],
outputs=[file_input, output],
)
# Launch the demo
if __name__ == "__main__":
demo.launch()
|