Hub
Pricing About
WorkflowWorkflow

Ollama - Chat with your PDF or Log Files - create and use a local vector store

OllamaLlama3LLMChatRAG
+5
mlauber71 profile image
Draft Latest edits on 
Aug 24, 2024 9:04 AM
Drag & drop
Like
Download workflow
Workflow preview
Ollama - Chat with your PDF or Log Files - create and use a local vector store

To keep up with the fast pace of local LLMs I try to use more generic nodes and Python code to access Ollama and Llama3 - this workflow will run with KNIME 4.7
The chroma vector store will be persisted in a local SQLite3 database.

To get this to work you will have to install Ollama and a Python environment with the necessary packages (py3_knime_llama), downlaod the Llama3 model and an embedding model (https://ollama.com/blog/embedding-models)

---
Medium: Llama3 and KNIME - Build your local Vector Store from PDFs and other Documents
https://medium.com/p/237eda761c1c

Medium - Chat with local Llama3 Model via Ollama in KNIME Analytics Platform - Also extract Logs into structured JSON Files
https://medium.com/p/aca61e4a690a

---
You can get more example of how to work with your documents by checking these Python Codes that you could then adapt
https://github.com/ml-score/

P.S.: yes I am aware of the large empty white space but I have no idea how to remove it in KNIME 4 and have already contacted KNIME support




External resources

  • Ollama - Embedding models
  • Chroma Vector Store
  • Medium: Llama3 and KNIME - Build your local Vector Store from PDFs and other Documents
  • GitHub - Work with Ollama and Llama models
  • Blog: Running models with Ollama step-by-step
  • KNIME - LLM Workspace on the Hub
  • Medium: Chat with local Llama3 Model via Ollama in KNIME Analytics Platform — Also extract Logs into structured JSON Files
  • Blog: Unleashing Conversational Power: A Guide to Building Dynamic Chat Applications with LangChain, Qdrant, and Ollama (or OpenAI’s GPT-3.5 Turbo)
  • Blog: Document Loaders in LangChain
  • Blog: Ask Questions from your CSV with an Open Source LLM, LangChain & a Vector DB
Loading deploymentsLoading ad hoc jobs

Used extensions & nodes

Created with KNIME Analytics Platform version 4.7.8 Note: Not all extensions may be displayed.
  • Go to item
    KNIME Base nodesTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.8

    knime
  • Go to item
    KNIME Conda IntegrationTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.0

    knime
  • Go to item
    KNIME DatabaseTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.4

    knime
  • Go to item
    KNIME Excel SupportTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.0

    knime
  • Go to item
    KNIME ExpressionsTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.3

    knime
  • Go to item
    KNIME JavaScript ViewsTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.0

    knime
  • Go to item
    KNIME JavasnippetTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.0

    knime
  • Go to item
    KNIME JSON-ProcessingTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.0

    knime
  • Go to item
    KNIME Math Expression (JEP)Trusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.0

    knime
  • Go to item
    KNIME Python IntegrationTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.3

    knime
  • Go to item
    KNIME Quick FormsTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 4.7.4

    knime

Legal

By using or downloading the workflow, you agree to our terms and conditions.

KNIME
Open for Innovation

KNIME AG
Talacker 50
8001 Zurich, Switzerland
  • Software
  • Getting started
  • Documentation
  • Courses + Certification
  • Solutions
  • KNIME Hub
  • KNIME Forum
  • Blog
  • Events
  • Partner
  • Developers
  • KNIME Home
  • Careers
  • Contact us
Download KNIME Analytics Platform Read more about KNIME Business Hub
© 2025 KNIME AG. All rights reserved.
  • Trademarks
  • Imprint
  • Privacy
  • Terms & Conditions
  • Data Processing Agreement
  • Credits