Latviešu valodā 1230 fakti http://tele2.asya.ai
Latviešu valodā 545 fakti http://tet.asya.ai
Ierobežojumi (demo)
Viena čata ietvaros lūdzu runāt par vienu tēmu, apakšā ir poga ar kuru sākt jaunu tēmu. Pašlaik sistēma cenšas atpazīt, ja tēma mainījusies, bet tā nav perfekta.
Sistēma šobrīd ir lēna, jo izmanto openai modeļus, bet to var paātrināt, ja pārejam uz mūsu modeļiem, kad esam noslēguši darījumu.
Šobrīd nav ieteicams vairāk par 5 papildjautājumiem vienas tēmas ietvaros
Jautājumi līdz 100 vārdiem šobrīd
Based on text similarity between ground truth chat and generated chat messages
Explanations:
Data Source
Existing client data that contains information needed to handle
Compute
Datasource formatting API - Takes data sources like PDFs, prior conversations and convert them into vector database (need to be adapted to customer needs)
Datasorce provider API - Provides Chatbot API with necessary information based on vector queries. This abstraction to ensure system can work with any Vector Databse - Exasol, PostgreSQL, Oracle etc. based on client needs
Text embedding API - Allows to convert natural language text into vector embeddings
LLM API - Large Language Model trained to be InstructGPT based model
Chatbot API - Main chatbot logic (need to be adapted to customer needs)
Vector Database
Any database to store vector and text chunks and other information like images, videos, sensor data etc.
UX - user experience for chatbot (can be actual app or just API)
Admin App - Special tool to see chatbot statistics and conversation flows, valuable conversational intelligence. Allows to modify chatbot behaviour in real time.