Found 23 bookmarks
Newest
Hands on with Deep Research
Hands on with Deep Research
Deep Research is the title of a new mode in several GenAI apps, including Google’s Gemini, OpenAI’s ChatGPT, and most recently, Perplexity. In this article, I will be focusing on the currently most hyped of these: OpenAI’s Deep Research. Although they weren’t first to release a product with this title (that was Google), they have […]
·leonfurze.com·
Hands on with Deep Research
Deep research System Card
Deep research System Card
OpenAI are rolling out their Deep research "agentic" research tool to their $20/month ChatGPT Plus users today, who get 10 queries a month. $200/month ChatGPT Pro gets 120 uses. Deep …
·simonwillison.net·
Deep research System Card
Curiosity - AI search for everything
Curiosity - AI search for everything
The ultimate AI productivity app that protects your privacy. Bring all your apps and data into one AI-powered search and assistant. Get it for you and for your teams today.
·curiosity.ai·
Curiosity - AI search for everything
Announcing The Assistant | Kagi Blog
Announcing The Assistant | Kagi Blog
Yes, the rumours are true! Kagi has been thoughtfully integrating AI into our search experience, creating a smarter, faster, and more intuitive search.
·blog.kagi.com·
Announcing The Assistant | Kagi Blog
Curiosity - AI search for everything
Curiosity - AI search for everything
The ultimate AI productivity app that protects your privacy. Bring all your apps and data into one AI-powered search and assistant. Get it for you and for your teams today.
·curiosity.ai·
Curiosity - AI search for everything
Exa API
Exa API
Exa API - connect your AI to the Internet
·exa.ai·
Exa API
nilsherzig/LLocalSearch: LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.
nilsherzig/LLocalSearch: LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.
LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progres...
·github.com·
nilsherzig/LLocalSearch: LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.
Tavily
Tavily
Say hello to Tavily, your AI researcher for rapid insights and comprehensive research.
·tavily.com·
Tavily
Google’s AI-powered search experience is way too slow - The Verge
Google’s AI-powered search experience is way too slow - The Verge

Google has introduced an experimental feature called Search Generative Experience (SGE) that uses AI to summarize search results, aiming to make search queries more complex and conversational. SGE is currently only available to people who sign up for Google’s waitlist on its Search Labs, where AI summaries appear right under the search box. The author of the article found the SGE responses generally accurate but cluttered with extra information, such as source information displayed as cards and potential follow-up prompts. The author criticized the SGE feature for its slow loading times, with some search results taking up to six seconds to load, which he found frustrating compared to the instant results of traditional Google Search. The SGE feature also returned error messages for some of the top-searched terms, such as "YouTube," "Amazon," "Wordle," "Twitter," and "Roblox," stating that an AI-powered overview was not available for these searches.

·theverge.com·
Google’s AI-powered search experience is way too slow - The Verge
ClippyGPT - How I Built Supabase’s OpenAI Doc Search (Embeddings)
ClippyGPT - How I Built Supabase’s OpenAI Doc Search (Embeddings)
Supabase hired me to build ClippyGPT - their next generation doc search. We can ask our old friend Clippy anything you want about Supabase, and it will answer it using natural language. Powered by OpenAI + prompt engineering. In this video I will be showing you exactly how I did this, and how you can do the same in your projects. We'll be covering: - Prompt engineering and best practices - Working with a custom knowledge base via context injection + OpenAI embeddings - How to store embeddings in Postgres using pgvector Supabase blog post: https://supabase.com/blog/chatgpt-supabase-docs pgvector extension: https://github.com/pgvector/pgvector Generate embeddings implementation: https://github.com/supabase/supabase/blob/54d39d4958575e5b58aa1d5d2a02db863ab4673c/apps/docs/scripts/generate-embeddings.ts Clippy edge function implementation: https://github.com/supabase/supabase/blob/54d39d4958575e5b58aa1d5d2a02db863ab4673c/supabase/functions/clippy-search/index.ts Clippy frontend implementation: https://github.com/supabase/supabase/blob/54d39d4958575e5b58aa1d5d2a02db863ab4673c/packages/ui/src/components/Command/AiCommand.tsx Prompt engineering: https://prmpts.ai/blog/what-is-prompt-engineering 00:00 Why? 01:40 Let's get started 03:15 Custom knowledge base 04:49 Context injection 06:13 Pre-process MDX files 13:40 Embeddings 15:40 Storing in Postgres + pgvector 22:21 API endpoint (edge function) 23:44 Calculating similarity in pgvector 27:55 Prompt engineering 33:15 Prompt best practices 38:37 Demo time! 41:32 Thanks for watching!
·youtube.com·
ClippyGPT - How I Built Supabase’s OpenAI Doc Search (Embeddings)