GPT4All - Ein lokaler LLM Vector Store auf Deutsch

0 ×

KNIME 5.2 unterstützt nun das Erstellen Ihrer eigenen Wissensdatenbank für LLMs, einen lokalen Vektorspeicher (FAISS), um Ihre eigenen Dokumente zu erkunden und sie mit KI zu befragen.

Workflow wurde adaptiert von diesem Beispiel:

https://hub.knime.com/-/spaces/-/~WNe6bb2w2bemYBWE/current-state/

URL: 4 levels of LLM customization - KNIME Blog https://www.knime.com/blog/4-levels-llm-customization
URL: AI Learnathons - KNIME Forum https://forum.knime.com/t/knime-ai-learnathons-are-here/73733
URL: How to Build AI-Powered Data Apps using KNIME - KNIME Webinar https://hopin.com/events/how-to-build-ai-powered-data-apps-using-knime-4bc6c73d-ae97-4c5f-be30-c0d8ea2dd52c
URL: MEDIUM Blog: KNIME, AI and local Large Language Models (LLM) https://medium.com/p/cef650fc142b
URL: GPT4All (download models) https://gpt4all.io/index.html
URL: forum entry (75594) https://forum.knime.com/t/gpt4all-embeddings/75594/5?u=mlauber71
URL: MEDIUM Blog: Creating a Local LLM Vector Store from PDFs with KNIME and GPT4All https://medium.com/p/311bf61dd20e
URL: Mistral-based model for German-language applications https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF
URL: FAISS (Facebook AI Similarity Search) https://ai.meta.com/tools/faiss/
URL: Blog: What’s New in KNIME Analytics Platform 5.2 https://www.knime.com/blog/whats-new-knime-analytics-platform-52
URL: Blog: RLHF: Reinforcement Learning from Human Feedback https://huyenchip.com/2023/05/02/rlhf.html

Nodes

• String Manipulation (Variable)10 ×
• String Manipulation9 ×
• GPT4All Embeddings Connector8 ×
• Create File/Folder Variables7 ×
• Table Row to Variable7 ×
• Show all 68 nodes

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Basic File System Connectors
• FeatureKNIME Excel Support
• FeatureKNIME HTML/PDF Writer (legacy)
• FeatureKNIME JavaScript Views
• Show all 9 modules

Links

• No links available