Яндекс.Метрика
qr-код - Как-то так стрелка - Как-то так
Leading Economist + ... пиктограмма - Как-то Так THIS     Экономическая грамотность и web-решения. Для тех кто считает деньги.
Персональная помощь в финансово-экономическом моделировании,
разработке простых CRM-систем (Laravel+Vue) и интеграции ИИ для вашего бизнеса
Идеи и проекты по оптимизации бизнеса - Связь !
If you don't like what you get, change what you give. © Carlos Castaneda     KAKTOTAK.BY - все услуги от экономического проектирования до разработки WEB-проектов: индивидуальных CRM-систем, онлайн-магазинов, лэндингов    Cooperation - on an ongoing basis    Be in the topic   -    SUBSCRIBE      My notes are ECONOMICS +  в Telegram   telegram  

How AI works with company documents: RAG, embeddings, and Qdrant

How AI works with company documents: RAG, embeddings, and Qdrant

For those who are interested in the process of integrating AI into business - using a simple example.

When AI starts working not with the Internet, but with your documents.

A little bit about what's going on "under the hood" to understand how AI finds the necessary information in the company's internal documents and turns it into a systematic response, rather than just searching for information on the Internet.

Imagine an enterprise with thousands of instructions, regulations, and technical documents.

The employee needs to know: «What needs to be checked before launching this equipment?»

Now he has to search for the right document, open it, browse dozens of pages, compare information from different documents and organize it himself in order to get an answer.

If there are thousands of documents, it can take hours to find the information you need. And a mistake or a missed point can be expensive.

Now imagine that an employee just asks this question in a corporate chat.
The system finds the necessary documents and specific fragments by itself, after which the AI generates a response and shows on the basis of which documents it was received.

An important point: The AI does not know the contents of the company's internal documents in advance. With each request, it first receives relevant fragments of documents in digital form from the corporate knowledge base, and only then uses this information to form a response.

RAG is used here (a system that allows AI to search for information in company documents).

Documents are split into fragments, and embeddings are created for them (converting text into a digital representation of its meaning). Embeddings and information about the corresponding fragments are then saved, for example, in Qdrant (a database for storing and searching such representations).

For general purposes, the process looks like this:

PDF documents of the company stored on the server

documents are divided into fragments

embeddings are created for fragments

embeddings and fragment information are saved in Qdrant

And when an employee asks a question:

The employee's question

the question is converted to embedding

the system searches in Qdrant for the closest fragments of documents

the found fragments are transmitted to LLM

LLM analyzes the question and the found information and generates a systematic answer with a link to the source document

At the same time, this entire AI part does not exist separately from the main program. It integrates into the same software stack that the system already runs on: for example, Laravel + Vue, Python + Django, Java + Spring, etc. In other words, you do not need to create a separate program for working with AI. The necessary components are connected to the existing system and work inside its business processes.

And here the main advantage is clearly visible.

Previously, people searched for information in documents and turned it into an answer themselves. Now the system finds the right place in thousands of documents by itself and turns the information found into an understandable answer.

At the same time, a person is not excluded from the process. He simply stops wasting time on mechanical search and processing of information. He gets quick access to corporate knowledge that used to be scattered across a huge array of documents.

That is, AI is not just a GPT chat, as many people perceive it today. It is a tool that can be embedded directly into a business process and made to work with real data, documents, and company tasks.

автор - Михаленко Р.
M R. Автор - kaktotak.by Specialization: financial and economic design - modeling of business, investment projects of the real sector, analysis and evaluation of efficiency, optimization of the management decision system.

A wide range of web-based competencies for solving business problems.

Subscribe to my telegram channel - My notes are ECONOMICS +
Там я ничего не втюхиваю и не навязываю. Просто делюсь некоторой интересной информацией по разным экономическим аспектам. Может, будет интересно !

  Personal assistance in economic design and web development:

  • Financial and economic modeling, analysis, accounting, business planning
  • Комплексная web-разработка/поддержка проекта в сети (php/js, seo – Laravel, WordPress, Vue, telegram, администрирование, контент, реклама в Яндекс Директ, интеграция ИИ

  telegram или форма обратной связи

Administrator
3

Currency Converter
RUB RUB-icon
USD USD-icon
EUR EUR-icon
CNY CNY-icon
BYN BYN-icon
UAH UAH-icon
KZT KZT-icon
SHORT- what is it about
ECONOMIC LITERACY
  Simple online solutions to problems of economics and finance  
I Want To Know Everything. Useful Tips