{"slug": "stem-image-text-based-pdf-textbooks-for-extraction-indexing-and-embeddings", "title": "STEM image/text based PDF textbooks for extraction, indexing and embeddings", "summary": "A developer is seeking a pipeline to convert STEM PDF textbooks into searchable embeddings, with stages for OCR-to-Markdown conversion, figure extraction, JSON schema structuring, and vector embeddings for Firestore Vector Search, and is asking for model suggestions that can run locally on a laptop with cloud storage for specific stages.", "body_md": "I am looking for the pipeline where the STEM (Science, Technology, Engineering and Math) textbooks which are in PDF format (images in pdf or text in pdf) to generate embeddings. the pipeline should achieve as below (or a better sub-stages)\n\n- stage1 - Converts scanned/image STEM PDFs into clean Markdown. It natively handles LaTeX equations (\\\\sum, \\\\int, powers x^2), multi-column reading orders, and tables without hallucinating. Run locally via GPU/CPU.\n- stage2 - isolates figure boxes and diagrams to save them separately in Cloud Storage for visual questions.\n- stage3 - Extracted Markdown is sent to build the canonical JSON schema (\n`Subject`\n\n\\\\rightarrow `Chapter`\n\n\\\\rightarrow `Topic`\n\n\\\\rightarrow `Concepts`\n\n).\n- stage4 - Generates vector embeddings for Firestore Vector Search to retrieve specific topics when building tests.\n\nany suggestions for the models.. where we performs a few stages in local laptop and maintain in cloud for only requried stages..", "url": "https://wpnews.pro/news/stem-image-text-based-pdf-textbooks-for-extraction-indexing-and-embeddings", "canonical_source": "https://discuss.huggingface.co/t/stem-image-text-based-pdf-textbooks-for-extraction-indexing-and-embeddings/179503#post_1", "published_at": "2026-08-31 12:05:40+00:00", "updated_at": "2026-08-31 12:22:56.264439+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "natural-language-processing", "ai-tools", "ai-infrastructure"], "entities": ["Firestore"], "alternates": {"html": "https://wpnews.pro/news/stem-image-text-based-pdf-textbooks-for-extraction-indexing-and-embeddings", "markdown": "https://wpnews.pro/news/stem-image-text-based-pdf-textbooks-for-extraction-indexing-and-embeddings.md", "text": "https://wpnews.pro/news/stem-image-text-based-pdf-textbooks-for-extraction-indexing-and-embeddings.txt", "jsonld": "https://wpnews.pro/news/stem-image-text-based-pdf-textbooks-for-extraction-indexing-and-embeddings.jsonld"}}