Spaces:
Sleeping
Sleeping
| import os | |
| import streamlit as st | |
| import PyPDF2 | |
| import matplotlib.pyplot as plt | |
| from io import BytesIO | |
| from llama_index.core import Settings, VectorStoreIndex, SimpleDirectoryReader | |
| from llama_index.embeddings.huggingface import HuggingFaceEmbedding | |
| from llama_index.llms.huggingface import HuggingFaceLLM | |
| import requests | |
| # Configure Hugging Face model | |
| Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5") | |
| Settings.llm = HuggingFaceLLM(model_name="sarvamai/sarvam-2b-v0.5", api_token=os.getenv("HUGGINGFACE_API_KEY")) | |
| def write_to_file(content, filename="./files/test.pdf"): | |
| os.makedirs(os.path.dirname(filename), exist_ok=True) | |
| with open(filename, "wb") as f: | |
| f.write(content) | |
| def ingest_documents(): | |
| reader = SimpleDirectoryReader("./files/") | |
| documents = reader.load_data() | |
| return documents | |
| def load_data(documents): | |
| index = VectorStoreIndex.from_documents(documents) | |
| return index | |
| def generate_summary(index, document_text): | |
| query_engine = index.as_query_engine() | |
| response = query_engine.query(f""" | |
| You are a financial analyst. Your task is to provide a comprehensive summary of the given financial document. | |
| Analyze the following document and summarize it: | |
| {document_text} | |
| Please cover the following aspects: | |
| 1. Revenue and profit trends | |
| 2. Key financial metrics | |
| 3. Major financial events and decisions | |
| 4. Comparison with previous periods | |
| 5. Future outlook or forecasts | |
| 6. Any notable financial risks or opportunities | |
| Provide a clear, concise, and professional summary | |
| """) | |
| return response.response | |
| def generate_comparison_graph(data): | |
| fig, ax = plt.subplots() | |
| ax.plot(data["Date"], data["Revenue"], marker="o") | |
| ax.set_title("Revenue Comparison") | |
| ax.set_xlabel("Date") | |
| ax.set_ylabel("Revenue (in millions)") | |
| st.pyplot(fig) | |
| # Streamlit app | |
| def main(): | |
| st.title("Financial Document Summarizer") | |
| st.write("Upload a financial document, and let our AI summarize it!") | |
| uploaded_file = st.file_uploader("Choose a financial document file", type=["pdf"]) | |
| if uploaded_file is not None: | |
| if uploaded_file.type == "application/pdf": | |
| pdf_reader = PyPDF2.PdfReader(BytesIO(uploaded_file.getvalue())) | |
| document_text = "" | |
| for page in pdf_reader.pages: | |
| document_text += page.extract_text() | |
| else: | |
| document_text = uploaded_file.getvalue().decode("utf-8") | |
| write_to_file(uploaded_file.getvalue()) | |
| st.write("Analyzing financial document...") | |
| documents = ingest_documents() | |
| index = load_data(documents) | |
| summary = generate_summary(index, document_text) | |
| st.write("## Financial Document Summary") | |
| st.write(summary) | |
| # Example data for graph (replace with actual data extraction logic) | |
| data = { | |
| "Date": ["Q1 2017", "Q2 2017", "Q1 2018", "Q2 2018"], | |
| "Revenue": [500, 550, 600, 620] | |
| } | |
| st.write("## Revenue Comparison") | |
| generate_comparison_graph(data) | |
| if __name__ == "__main__": | |
| main() | |