Spaces:
Runtime error
Runtime error
File size: 3,305 Bytes
370f105 ee5e4e0 03bce1c 370f105 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | import gradio as gr
import pandas as pd
import os
from langchain_community.document_loaders import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_community.vectorstores import Chroma
from langchain.chains import RetrievalQA
from transformers import pipeline
from langchain_community.llms import HuggingFacePipeline
print("Hi")
print('try')
# =========================
# LOAD PDF GUIDELINES
# =========================
PDF_PATH = "Lemonade_Guidlines.pdf"
loader = PyPDFLoader(PDF_PATH)
docs = loader.load()
# =========================
# CHUNKING
# =========================
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=500,
chunk_overlap=100
)
chunks = text_splitter.split_documents(docs)
# =========================
# EMBEDDINGS
# =========================
embedding_model = HuggingFaceEmbeddings(
model_name="sentence-transformers/all-MiniLM-L6-v2"
)
# =========================
# VECTOR DB (FASTER INIT)
# =========================
vectorstore = Chroma.from_documents(
documents=chunks,
embedding=embedding_model
)
retriever = vectorstore.as_retriever(search_kwargs={"k": 2})
# =========================
# LIGHTWEIGHT LLM (IMPORTANT FIX)
# =========================
pipe = pipeline(
"text-generation",
model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", # 🔥 small + fast
max_new_tokens=120,
temperature=0.2
)
llm = HuggingFacePipeline(pipeline=pipe)
# =========================
# QA CHAIN
# =========================
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
retriever=retriever
)
# =========================
# VIOLATION CHECK
# =========================
def check_violation(row):
prompt = f"""
You are a strict legal billing auditor.
Check if the below entry violates guidelines.
Narrative: {row['Narrative (Full Text)']}
Task Code: {row['Task Code']}
Timekeeper: {row['Timekeeper Name']}
Hours: {row['Units (Hrs / Qty)']}
Respond strictly:
Violation: Yes or No
Reason: <one line>
"""
try:
result = qa_chain.invoke({"query": prompt})
return result["result"]
except Exception as e:
return f"Error: {str(e)}"
# =========================
# FILE PROCESSING
# =========================
def process_file(file):
df = pd.read_excel(file, engine="openpyxl")
# Duplicate detection
df["Duplicate Count"] = df.duplicated(
subset=["Narrative (Full Text)", "Units (Hrs / Qty)", "Rate ($/Unit)"],
keep=False
).astype(int)
results = []
for i, row in df.iterrows():
# 🔥 LIMIT rows to avoid timeout (VERY IMPORTANT)
if i > 30:
results.append("Skipped (limit reached)")
continue
res = check_violation(row)
results.append(res)
df["Violation Analysis"] = results
output_path = "audited_output.xlsx"
df.to_excel(output_path, index=False)
return output_path
# =========================
# UI
# =========================
interface = gr.Interface(
fn=process_file,
inputs=gr.File(label="Upload Billing Excel"),
outputs=gr.File(label="Download Result"),
title="Legal Billing Auditor",
description="AI-powered billing audit using RAG"
)
interface.launch() |