SEARCH KEYWORD -- Business model


  Calculating Token Count for Claude API Using Go: A Step-by-Step Guide

When working with large language models like Claude from Anthropic, understanding how many tokens your input consumes is essential for managing costs and optimizing performance. In this blog, we’ll explore how to calculate token counts for a given input using Go. We’ll use Anthropic’s count_tokens API endpoint, which provides a straightforward way to determine token usage. Prerequisites Before diving in, ensure you have: A working Go environment (installation guide). An Anthro...

   CLAUDE,GO,GOLANG,TOKEN CALCULATION,GUIDE,EXAMPLE     2024-12-23 22:25:29

  The Best Laptops for Freelancers

Whether you’re answering emails, beating a deadline, or looking for even more freelance gigs, many professionals simply can’t imagine their career without a laptop. It has become the ultimate work gadget of the 21st century, which many laptops now powerful enough to be used like a PC. However, not all freelancers are the same—and as such, require different tools to get the job done. That being said, here are some of the best laptops for every kind of freelancer imaginable. Best...

   APPLE,COMPUTER,HP,LAPTOP     2020-03-04 07:58:12

  Google is developing advanced programming technology to simplify Web application development

Beijing, March 28. According to foreign media reports, Google engineer Alex Russell this week at EclipseCon meeting said the company is now developing lots of advanced programming techniques to simplify Web application development.Russell said, "Web development has come to a critical point, it is becoming a run-time library integration platform." Although Web is very popular compared to some platforms such as Java or Windows, it provides only a relatively original programming capability. A ...

   Google,Web,Dart,Scalability     2012-03-30 06:22:13

  Samijyon : A tablet from North Korea

According to Sina Tech, North Korea Tech posted an article about Samijyon. Samijyon is a model of Android  tablet manufactured by North Korea. You can buy it with $200 in North Korea. Smajiyon's hardware configuration is as good as Samsung and Apple, but it doesn't allow WiFi connection and ordinary North Koreans cannot connect to Internet as well, users can only connect to domestic network of North Korea. On this tablet, there are no built-in Google apps such as Gmail and Google Play. But...

   Samijyon,North Korea,Tablet     2013-08-03 22:01:35

  Google is returning back to China

It has been five years since Google announced its difficult decision to leave China in 2010. The well known reason was that Google didn't want to conform to China's censorship request on sensitive information. During these five years, many stories happened bbetween these two sides. Things may turn around now as there are a few indications where Google may return back to China at an appropriate time soon. The most convincing indication is that a customized Google play -- Google online shop may a...

   Google,China,Alphabet,Google play     2015-09-06 04:13:30

  Spurring the Consumer Feedback Loop with Connected Devices

In a press release from earlier this year, Gartner had predicted that by the year 2018 mobile devices would account for initiating 5% of consumer services cases, registering a marginal rise of 0.02% from 2014. Research shows that most businesses lose around a whopping $83 billion owing to poor consumer services (Source: kissmetrics) in the US alone while globally, the average cost of losing a consumer is $243. It is only viable to think of automating support services as a way to lower the costs ...

   Big Data Analytics Solutions, Loyalty Programs for Customers     2015-08-18 07:11:35

  Private LLM Integration with RAGFlow: A Step-by-Step Guide

If you’ve found your way here, you’re probably already excited about the potential of the RAGFlow project and eager to see it in action. I was in the same position, so I delved into the codebase to see how it could work with custom large language models (LLMs). This post will walk you through my findings and show you how to get RAGFlow running with your own LLM. As of now (November 8, 2024), RAGFlow offers limited support for local LLMs, and vLLM&nb...

   AI,LLM,RAGFLOW,RAG     2024-11-12 08:40:29

  CASSANDRA data model

Cassandra is an open source distributed database, it combines dynamic key/value and column oriented feature of Bigtable. Features of Cassandra are: Flexible schema, no need to design schema first, it's very convenient to add or delete strings Support range search on keys High usability, extensible. The single node error will not affect the cluster. We can think Cassandra's data model as a 4 or 5 dimensional Hash. COLUMN Columns is the smallest data unit in Cassandra, it is a 3 dimensional data...

   Cassandra,database,sort     2013-06-08 22:07:40

  Flows.network: Writing an LLM Application in Rust

Over the past year, large language models (LLMs) have been booming and developing vigorously. As an enthusiast of data systems, it would indeed seem outdated not to pursue and research this hot field at all. This article summarizes my recent practical experiences attempting to write an LLM application using Rust with flows.network. Concepts Related to Large Language Models When talking about large language models, it's impossible not to mention ChatGPT and OpenAI. Although OpenAI recently change...

   LLM,RUST,APPLICATION,DEVELOPMENT     2024-09-30 21:38:04

  Why is single threaded Redis so fast

Redis is a high-performance, in-memory key-value database. According to official test reports, it can support around 100,000 QPS (queries per second) on a single machine. However, Redis uses a single-threaded architecture in its design. Why does Redis still have such high performance with a single-threaded design? Wouldn't it be better to use multiple threads for concurrent request processing? In this article, let's explore why Redis has a single-threaded architecture and still maintains its spe...

   REDIS,SINGLE-THREADED,MULTI-THREADING     2023-02-28 05:16:22

RECENT