Uploaded February 2026 | Updated November 2026, 23 hours ago
Standard RAG lacks context, but full agentic scanning is too slow—so I designed a "Dual-Path" architecture to fix this. In this video, we build a hybrid system using DuckDB and Gemini that combines semantic search with metadata filtering to achieve high-accuracy retrieval without the latency. Join me as we upgrade our open-source agent with smart chunking and backtracking capabilities.
LINK:
Repo: github.com/PromtEngineer/agentic-file-search
Intro video: youtu.be/rMADSuus6jg
With Local Models: youtu.be/xG3eS_zHR3k
LangExtract Videos: youtu.be/RPpGIxmdZYs
youtu.be/dPL2vRDunMw
My voice to text App: whryte.com
Website: engineerprompt.ai
RAG Beyond Basics Course:
prompt-s-site.thinkific.com/courses/rag
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0
Let's Connect:
🦾 Discord: discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Patreon: patreon.com/PromptEngineering
💼Consulting: calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0
Standard RAG lacks context, but full agentic scanning is too slow—so I designed a "Dual-Path" architecture to fix this. In this video, we build a hybrid system using DuckDB and Gemini that combines semantic search with metadata filtering to achieve high-accuracy retrieval without the latency. Join me as we upgrade our open-source agent with smart chunking and backtracking capabilities.
LINK:
Repo: github.com/PromtEngineer/agentic-file-search
Intro video: youtu.be/rMADSuus6jg
With Local Models: youtu.be/xG3eS_zHR3k
LangExtract Videos: youtu.be/RPpGIxmdZYs
youtu.be/dPL2vRDunMw
My voice to text App: whryte.com
Website: engineerprompt.ai
RAG Beyond Basics Course:
prompt-s-site.thinkific.com/courses/rag
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0
Let's Connect:
🦾 Discord: discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Patreon: patreon.com/PromptEngineering
💼Consulting: calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: tinyurl.com/y5h28s6h
💻 Pre-configured localGPT VM: bit.ly/localGPT (use Code: PromptEngineering for 50% off).
Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

![Training Your Own Embedding Model Is Not As Hard As You Think
Fine-tune Embedding Gemma 2 (EmbeddingGemma 2) on your own data with Unsloth and LoRA in a free Colab notebook. I show how fine-tuning an embedding model differs from fine-tuning an LLM, then train Googles multimodal embedding model on two tasks: environmental sounds (ESC-50 top-1 24.5% to 65.8%) and search over my own YouTube transcripts (66.3% to 75.0% top-1 on videos it never saw), and check what it costs the rest of the model.
Youll learn how to build question-passage training pairs, why in-batch negatives (MultipleNegativesRankingLoss) need a no-duplicates sampler, why training and search prompts must match, how LoRA works on a shared multimodal backbone, how to evaluate on unseen data, and a reload bug that silently breaks audio adapters.
If you have fine-tuned embedding models for your own applications, share what worked for you in the comments.
Links:
Colab notebook: https://colab.research.google.com/drive/1xq-84DLZsqteEzL52Qb 47Y_yGckeyB?usp=sharing
The first EmbeddingGemma 2 video: [EMBEDDINGGEMMA 2 VIDEO LINK]
Unsloth EmbeddingGemma 2 guide: https://unsloth.ai/docs/models/embeddinggemma-2
Unsloth notebooks: https://github.com/unslothai/notebooks
Model card: https://huggingface.co/google/embeddinggemma-2
ESC-50 dataset: https://github.com/karolpiczak/ESC-50
Sentence Transformers losses: https://sbert.net/docs/package_reference/sentence_transformer/losses.html
00:00 - Fine-Tuning EmbeddingGemma 2 on Your Own Data
01:03 - Embedding Fine-Tuning vs LLM Fine-Tuning
02:30 - In-Batch Negatives (MultipleNegativesRankingLoss)
03:37 - The Duplicate Trap: No-Duplicates Sampler
04:45 - LoRA on a Shared Multimodal Backbone
06:30 - Notebook: ESC-50 Sounds with Unsloth on an A100
09:32 - Side Effects on Photo, Voice and Text Search
10:06 - Gotcha: Reloading an Audio Adapter
10:50 - Fine-Tuning on YouTube Transcripts
12:04 - Three Things to Get Right Training Your Own Embedding Model Is Not As Hard As You Think](https://i.ytimg.com/vi/S7tFyREI19I/mqdefault.jpg)






![98% of Qwen - Bonsai 2
Bonsai 2 from PrismML squeezes Qwen3.8 27B into a 6 GB file by retraining every weight to −1, 0 or +1, and PrismML claims it keeps 98% of the full models performance. On short tasks it matched the full model in my tests. Then I gave it a real job in an agentic loop: build an ISS tracker on a 3D globe. The full Qwen model built a working tracker. Bonsai never wrote a line of the app. It ran the exact same search 114 times and got the same answer every time.
Compression holds up for chat and quick coding help on a laptop. For long-running agentic tasks, test it on your own tasks before you trust the benchmarks.
Full comparison: [link to the full video]
#Bonsai2 #Qwen #LocalLLM #AIAgents #OpenSourceAI 98% of Qwen - Bonsai 2](https://i.ytimg.com/vi/TOmMp4SU144/mqdefault.jpg)

