This is a neat new variant on RAG - no vectors, not even full-text search, instead showing the model a header hierarchy and giving it a tool to read the relevant sections
My notes here: simonwillison.net/2024/Dec/6/r...
My notes here: simonwillison.net/2024/Dec/6/r...
December 6, 2024 at 3:04 AM
This is a neat new variant on RAG - no vectors, not even full-text search, instead showing the model a header hierarchy and giving it a tool to read the relevant sections
My notes here: simonwillison.net/2024/Dec/6/r...
My notes here: simonwillison.net/2024/Dec/6/r...
One more thing: RAG is not dying.
- Search + LLM = RAG
- Agent Search + LLM = still RAG
Remember:
The 'R' in RAG stands for Retrieval.
The 'AG' in RAG stands for Augmented Generation.
- Search + LLM = RAG
- Agent Search + LLM = still RAG
Remember:
The 'R' in RAG stands for Retrieval.
The 'AG' in RAG stands for Augmented Generation.
June 4, 2025 at 1:59 AM
One more thing: RAG is not dying.
- Search + LLM = RAG
- Agent Search + LLM = still RAG
Remember:
The 'R' in RAG stands for Retrieval.
The 'AG' in RAG stands for Augmented Generation.
- Search + LLM = RAG
- Agent Search + LLM = still RAG
Remember:
The 'R' in RAG stands for Retrieval.
The 'AG' in RAG stands for Augmented Generation.
Working on a lesson about the perils of LLM-based scientific search.
April 3, 2026 at 3:25 AM
Working on a lesson about the perils of LLM-based scientific search.
PacktPublishing / LLM-Engineers-Handbook
The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices
https://github.com/PacktPublishing/LLM-Engineers-Handbook
The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices
https://github.com/PacktPublishing/LLM-Engineers-Handbook
November 27, 2024 at 4:15 AM
PacktPublishing / LLM-Engineers-Handbook
The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices
https://github.com/PacktPublishing/LLM-Engineers-Handbook
The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices
https://github.com/PacktPublishing/LLM-Engineers-Handbook
The Mayo Clinic has come up with an approach to reduce LLM hallucinations.
Instead of RAG where relevant sources are included into the query to “ground” the result, their approach is to have the answer link back to authoritative sources. Then have a second LLM vet those citations.
Instead of RAG where relevant sources are included into the query to “ground” the result, their approach is to have the answer link back to authoritative sources. Then have a second LLM vet those citations.
Mayo Clinic’s secret weapon against AI hallucinations: Reverse RAG in action
To tackle data-retrieval-based hallucinations in non-diagnostic use cases, Mayo Clinic has applied CURE reverse RAG paired with vector databases.
venturebeat.com
March 15, 2025 at 10:57 PM
The Mayo Clinic has come up with an approach to reduce LLM hallucinations.
Instead of RAG where relevant sources are included into the query to “ground” the result, their approach is to have the answer link back to authoritative sources. Then have a second LLM vet those citations.
Instead of RAG where relevant sources are included into the query to “ground” the result, their approach is to have the answer link back to authoritative sources. Then have a second LLM vet those citations.
A common comment on my videos about LLM "hallucinations" is that this isn't as much of a problem because LLMs "cite their sources" now. This is a category error.
Citing a source implies it was consulted. LLMs do not consult, even with RAG. A citation might be *included* but it's not *consulted*.
Citing a source implies it was consulted. LLMs do not consult, even with RAG. A citation might be *included* but it's not *consulted*.
May 17, 2026 at 3:04 PM
A common comment on my videos about LLM "hallucinations" is that this isn't as much of a problem because LLMs "cite their sources" now. This is a category error.
Citing a source implies it was consulted. LLMs do not consult, even with RAG. A citation might be *included* but it's not *consulted*.
Citing a source implies it was consulted. LLMs do not consult, even with RAG. A citation might be *included* but it's not *consulted*.
Awesome LLM apps est un dépôt avec une grande collection d'applications orientées LLM avec des agents IA, du MCP, du RAG, ... Pour OpenAI, Anthropic, Gemini et autres modèles open sources ou open weight ⬇️
github.com/Shubhamsaboo...
github.com/Shubhamsaboo...
GitHub - Shubhamsaboo/awesome-llm-apps: Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models. - Shubhamsaboo/awesome-llm-apps
github.com
July 29, 2025 at 5:37 AM
Awesome LLM apps est un dépôt avec une grande collection d'applications orientées LLM avec des agents IA, du MCP, du RAG, ... Pour OpenAI, Anthropic, Gemini et autres modèles open sources ou open weight ⬇️
github.com/Shubhamsaboo...
github.com/Shubhamsaboo...
Anyone got a local LLM+RAG setup (for the popular "chat with your documents" / "chat with your data") that they find intuitive and useful?
I feel like local models - especially Llama 3.1 8B or Mistral Small 3 22B - should be capable for this more, what's the best software to run RAG with those?
I feel like local models - especially Llama 3.1 8B or Mistral Small 3 22B - should be capable for this more, what's the best software to run RAG with those?
March 3, 2025 at 3:55 PM
Anyone got a local LLM+RAG setup (for the popular "chat with your documents" / "chat with your data") that they find intuitive and useful?
I feel like local models - especially Llama 3.1 8B or Mistral Small 3 22B - should be capable for this more, what's the best software to run RAG with those?
I feel like local models - especially Llama 3.1 8B or Mistral Small 3 22B - should be capable for this more, what's the best software to run RAG with those?
This is a nice and clear "overview of the state of RAG"
hamel.dev/notes/llm/ra...
(via @arnicas.bsky.social's wonderful newsletter)
hamel.dev/notes/llm/ra...
(via @arnicas.bsky.social's wonderful newsletter)
P1: I don’t use RAG, I just retrieve documents – Hamel’s Blog
Ben Clavié’s introduction to advanced retrieval techniques
hamel.dev
July 3, 2025 at 6:17 AM
This is a nice and clear "overview of the state of RAG"
hamel.dev/notes/llm/ra...
(via @arnicas.bsky.social's wonderful newsletter)
hamel.dev/notes/llm/ra...
(via @arnicas.bsky.social's wonderful newsletter)
Vu que c'est Noël, voici un petit cadeau : awesome-llm-apps est un dépôt avec une curation de très nombreuses applications construites avec des LLM. Vous devriez certainement y trouver votre bonheur ⬇️
github.com/Shubhamsaboo...
github.com/Shubhamsaboo...
GitHub - Shubhamsaboo/awesome-llm-apps: Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.
Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models. - Shubhamsaboo/awesome-llm-apps
github.com
December 26, 2024 at 7:09 AM
Vu que c'est Noël, voici un petit cadeau : awesome-llm-apps est un dépôt avec une curation de très nombreuses applications construites avec des LLM. Vous devriez certainement y trouver votre bonheur ⬇️
github.com/Shubhamsaboo...
github.com/Shubhamsaboo...
ellmer: interact w/ any LLM in #Rstats
chores: automate repetitive tasks
gander: allow an LLM to talk to your R env
btw: describe your R env to an LLM
ragnar: RAG in R
vitals: LLM evals in R
kuzco: computer vision in R
mall: use an LLM for NLP on your data
doi.org/10.59350/z9f...
chores: automate repetitive tasks
gander: allow an LLM to talk to your R env
btw: describe your R env to an LLM
ragnar: RAG in R
vitals: LLM evals in R
kuzco: computer vision in R
mall: use an LLM for NLP on your data
doi.org/10.59350/z9f...
The Modern R Stack for Production AI
Python isn't the only game in town anymore: R can interact with local and cloud LLM APIs, inspect and modify your local R environment and files, implement RAG, computer vision, NLP, evals, & much more
doi.org
June 2, 2025 at 10:20 AM
ellmer: interact w/ any LLM in #Rstats
chores: automate repetitive tasks
gander: allow an LLM to talk to your R env
btw: describe your R env to an LLM
ragnar: RAG in R
vitals: LLM evals in R
kuzco: computer vision in R
mall: use an LLM for NLP on your data
doi.org/10.59350/z9f...
chores: automate repetitive tasks
gander: allow an LLM to talk to your R env
btw: describe your R env to an LLM
ragnar: RAG in R
vitals: LLM evals in R
kuzco: computer vision in R
mall: use an LLM for NLP on your data
doi.org/10.59350/z9f...
Hey fam 👋
In a new blog post, I wrote about my journey from zero to RAG engineer after 1200 hours building enterprise AI.
What actually works vs. what's just hype. Hard-learned lessons so you don't repeat my mistakes 👇
news.ycombinator.com/item?id=4474...
#TechBlog #BuildInPublic #RAG #AI #LLM
In a new blog post, I wrote about my journey from zero to RAG engineer after 1200 hours building enterprise AI.
What actually works vs. what's just hype. Hard-learned lessons so you don't repeat my mistakes 👇
news.ycombinator.com/item?id=4474...
#TechBlog #BuildInPublic #RAG #AI #LLM
From zero to RAG engineer: 1200 hours of lessons so you don't repeat my mistakes | Hacker News
news.ycombinator.com
July 31, 2025 at 8:05 AM
Hey fam 👋
In a new blog post, I wrote about my journey from zero to RAG engineer after 1200 hours building enterprise AI.
What actually works vs. what's just hype. Hard-learned lessons so you don't repeat my mistakes 👇
news.ycombinator.com/item?id=4474...
#TechBlog #BuildInPublic #RAG #AI #LLM
In a new blog post, I wrote about my journey from zero to RAG engineer after 1200 hours building enterprise AI.
What actually works vs. what's just hype. Hard-learned lessons so you don't repeat my mistakes 👇
news.ycombinator.com/item?id=4474...
#TechBlog #BuildInPublic #RAG #AI #LLM
AI term explained!
#AI #ArtificialIntelligence #ML #DL #NLP #chatbot #LLM #LLMs #technology #TechRevolution #tech #Engineering #AGI #RAG
#AI #ArtificialIntelligence #ML #DL #NLP #chatbot #LLM #LLMs #technology #TechRevolution #tech #Engineering #AGI #RAG
January 11, 2025 at 3:18 PM
AI term explained!
#AI #ArtificialIntelligence #ML #DL #NLP #chatbot #LLM #LLMs #technology #TechRevolution #tech #Engineering #AGI #RAG
#AI #ArtificialIntelligence #ML #DL #NLP #chatbot #LLM #LLMs #technology #TechRevolution #tech #Engineering #AGI #RAG
The Modern R Stack for Production AI: doi.org/10.59350/z9f...
Python isn't the only game in town anymore: R can interact with local and cloud LLM APIs, inspect and modify your local R environment and files, implement RAG, computer vision, NLP, evals, & much more #Rstats
Python isn't the only game in town anymore: R can interact with local and cloud LLM APIs, inspect and modify your local R environment and files, implement RAG, computer vision, NLP, evals, & much more #Rstats
The Modern R Stack for Production AI
Python isn't the only game in town anymore: R can interact with local and cloud LLM APIs, inspect and modify your local R environment and files, implement RAG, computer vision, NLP, evals, & much more
doi.org
June 2, 2025 at 10:20 AM
The Modern R Stack for Production AI: doi.org/10.59350/z9f...
Python isn't the only game in town anymore: R can interact with local and cloud LLM APIs, inspect and modify your local R environment and files, implement RAG, computer vision, NLP, evals, & much more #Rstats
Python isn't the only game in town anymore: R can interact with local and cloud LLM APIs, inspect and modify your local R environment and files, implement RAG, computer vision, NLP, evals, & much more #Rstats
okay but a RAG is still fundamentally an LLM
what you want is a better search engine
what you want is a better search engine
October 30, 2025 at 6:41 PM
okay but a RAG is still fundamentally an LLM
what you want is a better search engine
what you want is a better search engine
free idea for research: YapRAG, RAG and/or tool calling during the reasoning phase of a LLM response (RAG while the model is yapping)
January 31, 2025 at 10:57 AM
free idea for research: YapRAG, RAG and/or tool calling during the reasoning phase of a LLM response (RAG while the model is yapping)
Chunkr | Open Source Document Intelligence API
An open source API to convert documents into LLM/RAG ready chunks. It gives you granular control to balance speed, quality, and features—configurable exactly as you'd build it yourself.
github.com/lumina-ai-in...
An open source API to convert documents into LLM/RAG ready chunks. It gives you granular control to balance speed, quality, and features—configurable exactly as you'd build it yourself.
github.com/lumina-ai-in...
GitHub - lumina-ai-inc/chunkr: Vision infrastructure to turn complex documents into RAG/LLM-ready data
Vision infrastructure to turn complex documents into RAG/LLM-ready data - lumina-ai-inc/chunkr
github.com
March 7, 2025 at 3:39 AM
Chunkr | Open Source Document Intelligence API
An open source API to convert documents into LLM/RAG ready chunks. It gives you granular control to balance speed, quality, and features—configurable exactly as you'd build it yourself.
github.com/lumina-ai-in...
An open source API to convert documents into LLM/RAG ready chunks. It gives you granular control to balance speed, quality, and features—configurable exactly as you'd build it yourself.
github.com/lumina-ai-in...
🚀 Just published: "RAG from scratch with @docker.com Model Runner - Part 1"
Build a RAG system! Learn to create embeddings, & calculate vector similarities using Docker Model Runner & Go
🧠 #RAG #LLM #Docker #GoLang
🔗 k33g.hashnode.dev/rag-from-scr...
Build a RAG system! Learn to create embeddings, & calculate vector similarities using Docker Model Runner & Go
🧠 #RAG #LLM #Docker #GoLang
🔗 k33g.hashnode.dev/rag-from-scr...
April 20, 2025 at 1:47 PM
🚀 Just published: "RAG from scratch with @docker.com Model Runner - Part 1"
Build a RAG system! Learn to create embeddings, & calculate vector similarities using Docker Model Runner & Go
🧠 #RAG #LLM #Docker #GoLang
🔗 k33g.hashnode.dev/rag-from-scr...
Build a RAG system! Learn to create embeddings, & calculate vector similarities using Docker Model Runner & Go
🧠 #RAG #LLM #Docker #GoLang
🔗 k33g.hashnode.dev/rag-from-scr...
Ethical Hacking und Penetration Testing Tipps: Aufbau eines KI-Cybersicherheitslabors - Teil 11: LLM Benchmark's
#Ollama #HuggingFace #LocalLLM #KI #LLM #RAG #Quantization #Xubuntu #coolstuff
👇👇👇👇
youtu.be/E3f4Fubwjdc
#Ollama #HuggingFace #LocalLLM #KI #LLM #RAG #Quantization #Xubuntu #coolstuff
👇👇👇👇
youtu.be/E3f4Fubwjdc
September 28, 2026 at 4:53 AM
Ethical Hacking und Penetration Testing Tipps: Aufbau eines KI-Cybersicherheitslabors - Teil 11: LLM Benchmark's
#Ollama #HuggingFace #LocalLLM #KI #LLM #RAG #Quantization #Xubuntu #coolstuff
👇👇👇👇
youtu.be/E3f4Fubwjdc
#Ollama #HuggingFace #LocalLLM #KI #LLM #RAG #Quantization #Xubuntu #coolstuff
👇👇👇👇
youtu.be/E3f4Fubwjdc
Retrieval Augmented Generation (RAG) ist ein KI-Verfahren, das ein LLM mit einer guten Suche, z.B. in einer Dokumentensammlung, in einer Datenbank oder in einem Knowledge Graph ergänzt, um Antworten zu generieren.
Siehe auch Video (Kommentare).
www.iese.fraunhofer.de/blog/retriev...
Siehe auch Video (Kommentare).
www.iese.fraunhofer.de/blog/retriev...
Retrieval Augmented Generation (RAG): Chat mit eigenen Daten
RAG AI: Das KI-Verfahren Retrieval Augmented Generation (RAG) kombiniert Large Language Models (LLM) mit der Suche in Wissensquellen.
www.iese.fraunhofer.de
June 17, 2026 at 7:04 AM
Retrieval Augmented Generation (RAG) ist ein KI-Verfahren, das ein LLM mit einer guten Suche, z.B. in einer Dokumentensammlung, in einer Datenbank oder in einem Knowledge Graph ergänzt, um Antworten zu generieren.
Siehe auch Video (Kommentare).
www.iese.fraunhofer.de/blog/retriev...
Siehe auch Video (Kommentare).
www.iese.fraunhofer.de/blog/retriev...
🚀 Skyrocketing！ 🚀 (200+ new stars)
📦 Shubhamsaboo / awesome-llm-apps
⭐ 11,746 (+200)
🗒 Python
Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.
📦 Shubhamsaboo / awesome-llm-apps
⭐ 11,746 (+200)
🗒 Python
Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.
GitHub - Shubhamsaboo/awesome-llm-apps: Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.
Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models. - Shubhamsaboo/awesome-llm-apps
github.com
January 11, 2025 at 3:01 PM
🚀 Skyrocketing！ 🚀 (200+ new stars)
📦 Shubhamsaboo / awesome-llm-apps
⭐ 11,746 (+200)
🗒 Python
Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.
📦 Shubhamsaboo / awesome-llm-apps
⭐ 11,746 (+200)
🗒 Python
Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.
Multimodal RAG tutorial for beginners by Shaw Talebi 👇🏼
www.youtube.com/watch?v=Y7pN...
#LLM #AI #DataScience #RAG #Python
www.youtube.com/watch?v=Y7pN...
#LLM #AI #DataScience #RAG #Python
Multimodal RAG: A Beginner-friendly Guide (with Python Code)
YouTube video by Shaw Talebi
www.youtube.com
December 9, 2024 at 12:46 PM
Multimodal RAG tutorial for beginners by Shaw Talebi 👇🏼
www.youtube.com/watch?v=Y7pN...
#LLM #AI #DataScience #RAG #Python
www.youtube.com/watch?v=Y7pN...
#LLM #AI #DataScience #RAG #Python
Traditional AI vs Agentic AI vs RAG vs Agentic RAG — What's the Difference?
#ArtificialIntelligence #AI #RAG #AgenticRAG #AgenticAI #AIagentInnovation #AIAgents #GPT #LLMs #LLM #GenerativeAI #GenAI #technology #TechRevolution #tech #Engineering
#ArtificialIntelligence #AI #RAG #AgenticRAG #AgenticAI #AIagentInnovation #AIAgents #GPT #LLMs #LLM #GenerativeAI #GenAI #technology #TechRevolution #tech #Engineering
August 14, 2025 at 7:10 AM
Traditional AI vs Agentic AI vs RAG vs Agentic RAG — What's the Difference?
#ArtificialIntelligence #AI #RAG #AgenticRAG #AgenticAI #AIagentInnovation #AIAgents #GPT #LLMs #LLM #GenerativeAI #GenAI #technology #TechRevolution #tech #Engineering
#ArtificialIntelligence #AI #RAG #AgenticRAG #AgenticAI #AIagentInnovation #AIAgents #GPT #LLMs #LLM #GenerativeAI #GenAI #technology #TechRevolution #tech #Engineering