Spaces:
Runtime error
Runtime error
| import os | |
| import gradio as gr | |
| from pypdf import PdfReader | |
| from langchain_text_splitters import RecursiveCharacterTextSplitter | |
| from langchain_community.vectorstores import FAISS | |
| from langchain_community.document_loaders import PyPDFLoader | |
| from langchain_openai import OpenAIEmbeddings, ChatOpenAI | |
| from langchain_core.documents import Document | |
| # ------------------------- | |
| # Config | |
| # ------------------------- | |
| APP_TITLE = "Election Memory Engine" | |
| ARCHIVE_DIR = "archive" # put your PDFs inside this folder in the Space repo | |
| MODEL_NAME = "gpt-4o-mini" | |
| # ------------------------- | |
| # Document loading | |
| # ------------------------- | |
| def list_pdfs(root_dir: str): | |
| pdfs = [] | |
| for root, _, files in os.walk(root_dir): | |
| for f in files: | |
| if f.lower().endswith(".pdf"): | |
| pdfs.append(os.path.join(root, f)) | |
| return sorted(pdfs) | |
| def load_archive_docs(): | |
| pdf_paths = list_pdfs(ARCHIVE_DIR) | |
| docs = [] | |
| for path in pdf_paths: | |
| try: | |
| loader = PyPDFLoader(path) | |
| loaded = loader.load() | |
| # Ensure each page knows which file it came from | |
| for d in loaded: | |
| d.metadata = d.metadata or {} | |
| d.metadata["source"] = os.path.basename(path) | |
| docs.extend(loaded) | |
| except Exception: | |
| # Fallback: try simple reader if loader fails | |
| try: | |
| reader = PdfReader(path) | |
| text = "\n".join([(p.extract_text() or "") for p in reader.pages]) | |
| docs.append(Document(page_content=text, metadata={"source": os.path.basename(path)})) | |
| except Exception: | |
| continue | |
| return docs | |
| # ------------------------- | |
| # Index build (startup) | |
| # ------------------------- | |
| def build_vectorstore(): | |
| docs = load_archive_docs() | |
| if not docs: | |
| return None, "No PDFs found. Upload PDFs into the `archive/` folder in Files." | |
| splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150) | |
| chunks = splitter.split_documents(docs) | |
| embeddings = OpenAIEmbeddings(model="text-embedding-3-small") | |
| vs = FAISS.from_documents(chunks, embeddings) | |
| return vs, f"✅ Indexed {len(docs)} pages/sections from {len(set([d.metadata.get('source','') for d in docs]))} file(s)." | |
| VECTORSTORE, INDEX_STATUS = build_vectorstore() | |
| # ------------------------- | |
| # Answering with sources | |
| # ------------------------- | |
| def answer_question(question: str): | |
| if VECTORSTORE is None: | |
| return INDEX_STATUS | |
| if not question or not question.strip(): | |
| return "Type a question first." | |
| retriever = VECTORSTORE.as_retriever(search_kwargs={"k": 5}) | |
| hits = retriever.get_relevant_documents(question) | |
| # Build a compact context for the model + collect citations | |
| context_parts = [] | |
| cite_lines = [] | |
| for i, d in enumerate(hits, start=1): | |
| src = d.metadata.get("source", "unknown") | |
| excerpt = " ".join(d.page_content.split())[:260] | |
| cite_lines.append(f"{i}. **{src}** — {excerpt}…") | |
| context_parts.append(f"[Source {i}: {src}]\n{d.page_content}") | |
| llm = ChatOpenAI(model=MODEL_NAME, temperature=0.2) | |
| prompt = f""" | |
| You are an archive assistant for an election newsroom. | |
| Answer using ONLY the context below. If the context is insufficient, say what is missing and suggest what document would help. | |
| Write in a newsroom-ready format: | |
| - 5–8 bullet background points | |
| - If dates exist, include a short timeline | |
| - End with "Sources used: 1,2,3..." | |
| Question: {question} | |
| Context: | |
| {chr(10).join(context_parts)} | |
| """.strip() | |
| resp = llm.invoke(prompt).content | |
| citations = "\n".join(cite_lines) if cite_lines else "_No sources returned._" | |
| return f"{resp}\n\n---\n### Sources (snippets)\n{citations}" | |
| # ------------------------- | |
| # UI | |
| # ------------------------- | |
| CUSTOM_CSS = """ | |
| @import url('https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:wght@400;600;700&display=swap'); | |
| .gradio-container{ | |
| background: white !important; | |
| font-family: 'IBM Plex Mono', monospace !important; | |
| } | |
| h1{ | |
| font-size:52px !important; | |
| font-weight:800 !important; | |
| line-height:1.05 !important; | |
| letter-spacing:-1px; | |
| } | |
| h3{ | |
| color:#6b7280 !important; | |
| font-weight:400 !important; | |
| } | |
| button{ | |
| border-radius: 12px !important; | |
| padding: 12px 24px !important; | |
| font-weight: 600 !important; | |
| } | |
| .gradio-container > div:first-child { | |
| border-bottom: 1px solid #e5e7eb; | |
| padding-bottom: 20px; | |
| margin-bottom: 26px; | |
| } | |
| """ | |
| LOGO_PATH = "assets/archive logo.png" | |
| HERO_PATH = "assets/file cabinet.png" | |
| def load_pil(path: str): | |
| try: | |
| from PIL import Image | |
| if os.path.exists(path): | |
| return Image.open(path) | |
| except Exception: | |
| return None | |
| return None | |
| with gr.Blocks(css=CUSTOM_CSS, title=APP_TITLE) as demo: | |
| # Navbar | |
| with gr.Row(): | |
| with gr.Column(scale=1, min_width=70): | |
| logo = load_pil(LOGO_PATH) | |
| if logo is not None: | |
| gr.Image(value=logo, show_label=False, container=False, height=44) | |
| else: | |
| gr.Markdown("<span style='color:#6b7280;font-size:12px;'>Logo missing</span>") | |
| with gr.Column(scale=5): | |
| gr.Markdown("<div style='font-weight:700; font-size:18px; padding-top:6px;'>Election Archive</div>") | |
| with gr.Column(scale=6): | |
| gr.HTML( | |
| """ | |
| <div style="display:flex; justify-content:flex-end; gap:28px; font-weight:500; padding-top:10px;"> | |
| <span>Home</span> | |
| <span>Archive</span> | |
| <span>Upload</span> | |
| </div> | |
| """ | |
| ) | |
| # Hero | |
| with gr.Row(): | |
| with gr.Column(scale=6): | |
| gr.Markdown(""" | |
| # What Happened | |
| # Last | |
| # Election? | |
| ### Turn your newsroom archive into a searchable memory engine. | |
| ### Upload documents. Ask questions. Get answers with sources. | |
| """) | |
| gr.Markdown(f"<div style='color:#6b7280; font-size:12px;'>Index status: {INDEX_STATUS}</div>") | |
| with gr.Column(scale=6): | |
| hero = load_pil(HERO_PATH) | |
| if hero is not None: | |
| gr.Image(value=hero, show_label=False, container=False) | |
| else: | |
| gr.Markdown("<span style='color:#6b7280;font-size:12px;'>Hero image missing</span>") | |
| # Search / Q&A | |
| with gr.Row(): | |
| with gr.Column(): | |
| q = gr.Textbox( | |
| label="Ask the archive", | |
| placeholder="e.g. What were the major issues in 2022, and what patterns repeat from 2017?", | |
| ) | |
| out = gr.Markdown() | |
| btn = gr.Button("Search", variant="primary") | |
| btn.click(answer_question, q, out) | |
| q.submit(answer_question, q, out) | |
| demo.launch() |