File size: 3,335 Bytes
3430157 fada25c 3430157 fada25c f99df60 |
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 |
import os
from dotenv import load_dotenv
import gradio as gr
from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
from llama_index.llms.huggingface import HuggingFaceInferenceAPI
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from sentence_transformers import SentenceTransformer
from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate, Settings
load_dotenv()
# Configure the Llama index settings
Settings.llm = HuggingFaceInferenceAPI(
model_name="google/gemma-1.1-7b-it",
tokenizer_name="google/gemma-1.1-7b-it",
context_window=3000,
token=os.getenv("HF_TOKEN"),
max_new_tokens=512,
generate_kwargs={"temperature": 0.1},
)
Settings.embed_model = HuggingFaceEmbedding(
model_name="BAAI/bge-small-en-v1.5"
)
# Define the directory for persistent storage and data
PERSIST_DIR = "db"
PDF_DIRECTORY = 'data' # Changed to the directory containing PDFs
# Ensure PDF directory exists
os.makedirs(PDF_DIRECTORY, exist_ok=True)
os.makedirs(PERSIST_DIR, exist_ok=True)
def data_ingestion_from_directory():
# Use SimpleDirectoryReader on the directory containing the PDF files
documents = SimpleDirectoryReader(PDF_DIRECTORY).load_data()
storage_context = StorageContext.from_defaults()
index = VectorStoreIndex.from_documents(documents)
index.storage_context.persist(persist_dir=PERSIST_DIR)
def handle_query(query):
chat_text_qa_msgs = [
(
"user",
"""
You are a Q&A assistant named RedfernsTech, created by the RedfernsTech team. You have been designed to provide accurate answers based on the context provided.
Context:
{context_str}
Question:
{query_str}
"""
)
]
text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
# Load index from storage
storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
index = load_index_from_storage(storage_context)
query_engine = index.as_query_engine(text_qa_template=text_qa_template)
answer = query_engine.query(query)
if hasattr(answer, 'response'):
return answer.response
elif isinstance(answer, dict) and 'response' in answer:
return answer['response']
else:
return "Sorry, I couldn't find an answer."
# Example usage
# Process PDF ingestion from directory
print("Processing PDF ingestion from directory:", PDF_DIRECTORY)
data_ingestion_from_directory()
# Example query
query = "How do I use the RedfernsTech Q&A assistant?"
print("Query:", query)
response = handle_query(query)
print("Answer:", response)
# prompt: create a gradio chatbot for this
# Define the input and output components for the Gradio interface
input_component = gr.Textbox(
show_label=False,
placeholder="Ask me anything about the document..."
)
output_component = gr.Textbox()
# Create the Gradio interface
interface = gr.Interface(
fn=handle_query,
inputs=input_component,
outputs=output_component,
title="RedfernsTech Q&A Chatbot",
description="Ask me anything about the uploaded document."
)
# Launch the Gradio interface
interface.launch()
|