Mulai 29 April 2025, model Gemini 1.5 Pro dan Gemini 1.5 Flash tidak tersedia di project yang belum pernah menggunakan model ini, termasuk project baru. Untuk mengetahui detailnya, lihat Versi dan siklus proses model.
Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Halaman ini memberikan prasyarat dan petunjuk mendetail untuk menyesuaikan Gemini pada data dokumen menggunakan pembelajaran terawasi.
Kasus penggunaan
Penyesuaian memungkinkan Anda menyesuaikan model bahasa yang canggih untuk kebutuhan spesifik Anda.
Berikut beberapa kasus penggunaan utama saat penyesuaian dengan kumpulan PDF Anda sendiri dapat meningkatkan performa model secara signifikan:
Pusat informasi internal: Ubah dokumen internal Anda menjadi pusat informasi yang didukung AI yang memberikan jawaban dan insight secara instan. Misalnya, tenaga penjualan dapat langsung mengakses spesifikasi produk dan detail harga dari materi pelatihan sebelumnya.
Asisten riset: Buat asisten riset yang mampu menganalisis kumpulan makalah penelitian, artikel, dan buku. Seorang peneliti yang mempelajari perubahan iklim dapat dengan cepat menganalisis makalah ilmiah untuk mengidentifikasi tren kenaikan permukaan laut atau menilai efektivitas berbagai strategi mitigasi.
Kepatuhan terhadap hukum atau peraturan: Penyesuaian pada dokumen hukum dapat membantu mengotomatiskan peninjauan kontrak, menandai potensi inkonsistensi atau area risiko. Dengan begitu, profesional hukum dapat berfokus pada tugas tingkat yang lebih tinggi sekaligus memastikan kepatuhan.
Pembuatan laporan otomatis: Otomatiskan analisis laporan keuangan yang kompleks, ekstrak indikator performa utama, dan buat ringkasan untuk pemangku kepentingan. Hal ini dapat menghemat waktu dan mengurangi risiko kesalahan dibandingkan dengan analisis manual.
Ringkasan dan analisis konten: Meringkas dokumen PDF yang panjang, mengekstrak insight utama, dan menganalisis tren. Misalnya, tim riset pasar dapat menganalisis kumpulan survei pelanggan untuk mengidentifikasi tema dan sentimen utama.
Perbandingan dokumen dan kontrol versi: Bandingkan berbagai versi dokumen untuk mengidentifikasi perubahan dan melacak revisi. Hal ini dapat sangat berguna dalam lingkungan kolaboratif di mana beberapa penulis berkontribusi pada dokumen.
{"contents":[{"role":"user","parts":[{"fileData":{"mimeType":"application/pdf","fileUri":"gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf"}},{"text":"You are a very professional document summarization specialist. Please summarize the given document."}]},{"role":"model","parts":[{"text":"The report introduces Gemini 2.0 Flash, a multimodal AI model developed by Google DeepMind. The report positions Gemini 2.0 Flash as a significant advancement in multimodal AI, pushing the boundaries of long-context understanding and opening new avenues for future research and applications."}]}]}
Langkah berikutnya
Untuk mempelajari lebih lanjut kemampuan pemahaman dokumen model Gemini, lihat ringkasan Pemahaman dokumen.
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-08-25 UTC."],[],[],null,["# Document tuning\n\nThis page provides prerequisites and detailed instructions for fine-tuning\nGemini on document data using supervised learning.\n\nUse cases\n---------\n\nFine-tuning lets you customize powerful language models for your specific needs.\nHere are some key use cases where fine-tuning with your own set of PDFs can\nsignificantly enhance a model's performance:\n\n- **Internal knowledge base**: Convert your internal documents into an AI-powered knowledge base that provides instant answers and insights. For example, a sales representative could instantly access product specifications and pricing details from past training materials.\n- **Research assistant**: Create a research assistant capable of analyzing a collection of research papers, articles, and books. A researcher studying climate change could quickly analyze scientific papers to identify trends in sea level rise or assess the effectiveness of different mitigation strategies.\n- **Legal or regulatory compliance**: Fine-tuning on legal documents can help automate contract review, flagging potential inconsistencies or areas of risk. This allows legal professionals to focus on higher-level tasks while ensuring compliance.\n- **Automated report generation**: Automate the analysis of complex financial reports, extracting key performance indicators and generating summaries for stakeholders. This can save time and reduce the risk of errors compared to manual analysis.\n- **Content summarization and analysis**: Summarize lengthy PDF documents, extract key insights, and analyze trends. For example, a market research team could analyze a collection of customer surveys to identify key themes and sentiment.\n- **Document comparison and version control**: Compare different versions of a document to identify changes and track revisions. This can be particularly useful in collaborative environments where multiple authors contribute to a document.\n\nLimitations\n-----------\n\n### Gemini 2.5 models\n\n### Gemini 2.0 Flash\nGemini 2.0 Flash-Lite\n\nTo learn more about document understanding requirements, see [Document understanding](/vertex-ai/generative-ai/docs/multimodal/document-understanding#document-requirements).\n\nDataset format\n--------------\n\nThe `fileUri` for your dataset can be the URI for a file in a Cloud Storage\nbucket, or it can be a publicly available HTTP or HTTPS URL.\n\nTo see the generic format example, see\n[Dataset example for Gemini](/vertex-ai/generative-ai/docs/models/gemini-supervised-tuning-prepare#dataset-example).\n\nThe following is an example of a document dataset. \n\n {\n \"contents\": [\n {\n \"role\": \"user\",\n \"parts\": [\n {\n \"fileData\": {\n \"mimeType\": \"application/pdf\",\n \"fileUri\": \"gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf\"\n }\n },\n {\n \"text\": \"You are a very professional document summarization specialist. Please summarize the given document.\"\n }\n ]\n },\n {\n \"role\": \"model\",\n \"parts\": [\n {\n \"text\": \"The report introduces Gemini 2.0 Flash, a multimodal AI model developed by Google DeepMind. The report positions Gemini 2.0 Flash as a significant advancement in multimodal AI, pushing the boundaries of long-context understanding and opening new avenues for future research and applications.\"\n }\n ]\n }\n ]\n }\n\nWhat's next\n-----------\n\n- To learn more about the document understanding capability of Gemini models, see the [Document understanding](/vertex-ai/generative-ai/docs/multimodal/document-understanding) overview.\n- To start tuning, see [Tune Gemini models by using supervised fine-tuning](/vertex-ai/generative-ai/docs/models/gemini-use-supervised-tuning)\n- To learn how supervised fine-tuning can be used in a solution that builds a generative AI knowledge base, see [Jump Start Solution: Generative AI\n knowledge base](/architecture/ai-ml/generative-ai-knowledge-base)."]]