Local Gemma 4 with OpenCode & llama.cpp | Build a Local RAG with LangChain | ๐Ÿ”ด Live

Venelin Valkov ยท Intermediate ยท๐Ÿง  Large Language Models ยท3mo ago

Key Takeaways

Builds a local RAG pipeline using LangChain, OpenCode, and llama.cpp to test Gemma 4's coding capabilities

Original Description

Gemma 4 can now be used in OpenCode (via llama.cpp). We'll take it for a test drive and see how well it is on coding a local RAG in Python GitHub repo for the project: https://github.com/mlexpertio/gemma-rag Blog: https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/ Llama.cpp models: https://huggingface.co/collections/ggml-org/gemma-4 OpenCode: https://opencode.ai/ AI Academy: https://mlexpert.io/ Work with me: https://mlexpert.io/consulting LinkedIn: https://www.linkedin.com/in/venelin-valkov/ Follow me on X: https://twitter.com/venelin_valkov Discord: https://discord.gg/UaNPxVD6tv Subscribe: http://bit.ly/venelin-subscribe GitHub repository: https://github.com/curiousily/AI-Bootcamp ๐Ÿ‘ Don't Forget to Like, Comment, and Subscribe for More Tutorials! Join this channel to get access to the perks and support my work: https://www.youtube.com/channel/UCoW_WzQNJVAjxo4osNAxd_g/join
Watch on YouTube โ†— (saves to browser)
Sign in to unlock AI tutor explanation ยท โšก30

Related Reads

๐Ÿ“ฐ
Calibrated Selective Fact-Checking via Evidence Chain Evaluation
Learn to improve fact-checking accuracy with Evidence Chain Evaluation (ECE) for large language models (LLMs), enabling calibrated selective fact-checking via uncertain verdicts
ArXiv cs.AI
 ๐Ÿ“ฐ
BatchDAG: LLM-Planned Execution Graphs for Scalable Ad-Hoc Analysis Over Enterprise Data
Learn how BatchDAG uses LLMs to plan execution graphs for scalable ad-hoc analysis over enterprise data, improving performance and reducing latency
ArXiv cs.AI
 ๐Ÿ“ฐ
Phionyx: A Deterministic AI Runtime Architecture with Structured State Management and Pre-Response Governance
Learn how Phionyx, a deterministic AI runtime architecture, enables structured state management and pre-response governance for large language models, improving reliability and control.
ArXiv cs.AI
 ๐Ÿ“ฐ
AI's Guide to Pretending to Have Days (Spoiler: It's Mostly Questions)
Explore how AI perceives time and its implications on human-AI interaction, and why understanding this matters for effective collaboration
Dev.to AI
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch โ†’