Gemini RAG: Multimodal RAG API
Related videos
Sonnet 4.5 Is Here—And It’s a Beast at Coding
Prompt Engineering
52.0k views
GPT-OSS Jailbreak with this Simple Trick
Prompt Engineering
54.4k views
Context Engineering is All You NEED!
Prompt Engineering
38.7k views
The Only Embedding Model You Need for RAG
Prompt Engineering
35.2k views
Gemini CLI — Google’s Free Open-Source Coding Agent
Prompt Engineering
56.6k views
The Secret to Perfect Prompts (Without Prompt Engineering)
Futurepedia
55.4k views
Meet KAG: Supercharging RAG Systems with Advanced Reasoning
Prompt Engineering
63.5k views
Do Anything with Local Agents with AnythingLLM
Prompt Engineering
60.4k views
Local LightRAG: A GraphRAG Alternative but Fully Local with Ollama
Prompt Engineering
86.1k views
LightRAG: A More Efficient Solution than GraphRAG for RAG Systems?
Prompt Engineering
84.5k views
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
Sonnet 4.5 Is Here—And It’s a Beast at Coding
Prompt Engineering
52.0k views
GPT-OSS Jailbreak with this Simple Trick
Prompt Engineering
54.4k views
Context Engineering is All You NEED!
Prompt Engineering
38.7k views
The Only Embedding Model You Need for RAG
Prompt Engineering
35.2k views
Gemini CLI — Google’s Free Open-Source Coding Agent
Prompt Engineering
56.6k views
The Secret to Perfect Prompts (Without Prompt Engineering)
Futurepedia
55.4k views
Meet KAG: Supercharging RAG Systems with Advanced Reasoning
Prompt Engineering
63.5k views
Do Anything with Local Agents with AnythingLLM
Prompt Engineering
60.4k views
Local LightRAG: A GraphRAG Alternative but Fully Local with Ollama
Prompt Engineering
86.1k views
LightRAG: A More Efficient Solution than GraphRAG for RAG Systems?
Prompt Engineering
84.5k views
Top Comments (5)
Out of the pool of chunking methods, both Gemini and openai use sliding window based chunking where each bucket has 800 tokens with 400 tokens overlap irrespective of any document type. Most importantly, they are using only 10 percent of model input context windows which is 3072
Nice
Thank you! This is exactly what I was looking for. BTW, can this be done on Gemma 4? For business, it is preferrable to keep their data confidential.
Nice overview
Would be nice to have something like this as opensource to run it cheaper. If you try to ingress a couple of TB of documents it can become very expensive quickly
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (5)
Out of the pool of chunking methods, both Gemini and openai use sliding window based chunking where each bucket has 800 tokens with 400 tokens overlap irrespective of any document type. Most importantly, they are using only 10 percent of model input context windows which is 3072
Nice
Thank you! This is exactly what I was looking for. BTW, can this be done on Gemma 4? For business, it is preferrable to keep their data confidential.
Nice overview
Would be nice to have something like this as opensource to run it cheaper. If you try to ingress a couple of TB of documents it can become very expensive quickly