File size: 2,087 Bytes
ade8cf8 21583be ade8cf8 21583be ade8cf8 95269b9 ade8cf8 95269b9 ade8cf8 21583be ade8cf8 21583be ade8cf8 21583be ade8cf8 21583be ade8cf8 21583be 95269b9 ade8cf8 |
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 |
from transformers import RagTokenizer, RagTokenForGeneration, AutoTokenizer, AutoModelForCausalLM, pipeline
from pdfminer.high_level import extract_text
from docx import Document
from dataclasses import dataclass
import pandas as pd
# Initialize RAG
rag_tokenizer = RagTokenizer.from_pretrained("facebook/rag-token-nq")
rag_model = RagTokenForGeneration.from_pretrained("facebook/rag-token-nq")
# Initialize Phi-2
phi_tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2", trust_remote_code=True)
phi_model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", trust_remote_code=True)
@dataclass
class Paragraph:
page_num: int
paragraph_num: int
content: str
def read_pdf_pdfminer(file_path) -> list[Paragraph]:
text = extract_text(file_path).replace('\n', ' ').strip()
paragraphs = text.split(". ")
return [Paragraph(0, i, para) for i, para in enumerate(paragraphs, 1)]
def read_docx(file) -> list[Paragraph]:
doc = Document(file)
return [Paragraph(1, i, para.text.strip()) for i, para in enumerate(doc.paragraphs, 1) if para.text.strip()]
def generate_context_with_rag(question: str) -> str:
inputs = rag_tokenizer(question, return_tensors="pt")
output_ids = rag_model.generate(**inputs)
context = rag_tokenizer.decode(output_ids[0], skip_special_tokens=True)
return context
def generate_answer_with_phi(question: str, context: str) -> str:
enhanced_question = f"Question: {question}\nContext: {context}\nAnswer:"
inputs = phi_tokenizer.encode(enhanced_question, return_tensors="pt", max_length=512, truncation=True)
outputs = phi_model.generate(inputs, max_length=600)
answer = phi_tokenizer.decode(outputs[0], skip_special_tokens=True)
return answer
def answer_question(question: str, documents_df: pd.DataFrame) -> str:
# Assuming documents_df contains the text from uploaded files
combined_text = " ".join(documents_df['content'].tolist())
context = generate_context_with_rag(combined_text + " " + question)
answer = generate_answer_with_phi(question, context)
return answer
|