File size: 1,349 Bytes
018fb30 037c950 018fb30 037c950 c52adb8 037c950 018fb30 2b75a1c 018fb30 037c950 018fb30 037c950 018fb30 037c950 018fb30 037c950 018fb30 037c950 |
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 |
import gradio as gr
import os
from langchain.vectorstores import Chroma
from langchain.document_loaders import PyPDFLoader
from langchain.embeddings import HuggingFaceInferenceAPIEmbeddings
# Use Hugging Face Inference API embeddings
inference_api_key = os.environ['hf']
api_hf_embeddings = HuggingFaceInferenceAPIEmbeddings(
api_key=inference_api_key,
model_name="sentence-transformers/all-MiniLM-l6-v2"
)
# Load and process the PDF files
loader = PyPDFLoader("./new_papers/ReACT.pdf")
documents = loader.load()
# Create Chroma vector store for API embeddings
api_db = Chroma.from_documents(documents, api_hf_embeddings, collection_name="api-collection")
class PDFRetrievalTool:
def __init__(self, retriever):
self.retriever = retriever
def __call__(self, query):
# Run the query through the retriever
response = self.retriever.run(query)
return response['result']
# Create Gradio interface for the API retriever
api_tool = gr.Interface(
PDFRetrievalTool(api_db.as_retriever(search_kwargs={"k": 1})),
inputs=gr.Textbox(),
outputs=gr.Textbox(),
live=True,
title="API PDF Retrieval Tool",
description="This tool indexes PDF documents and retrieves relevant answers based on a given query (HF Inference API Embeddings).",
)
# Launch the Gradio interface
api_tool.launch()
|