Keywords: RAG, LangChain, Transformers, NLTK, LlamaIndex

• Development of chatbots that can utilize accumulated organizational knowledge
• Building a question answering system based on in-house technical reports and customer interaction logs
• Automated performance evaluation of AI chatbots
• Continuous automated evaluation of AI chatbot performance from various perspectives
• Developing advanced interfaces in ChatGPT style
• Development of features such as prompt saving, sharing, parallel execution, and external system integration

Keywords: AI Agent, Vision Language Models, Model Context Protocol

• Development of AI agents to streamline R&D operations
• Automating R&D operations by customizing LangGraph, CrewAI, Swarm, etc.
• Integration of AI code generation into your development environment
• Development of an AI-powered IDE specialized for your development environment
• Integration of AI agents with existing applications
• Development and performance optimization of interfaces between your applications and AI agents

Keywords: Local LLM, SLM

• Implementation and tuning of local LLMs running in on-premises environments
• Developing chatbot systems that can be used without exposing confidential data
• Development of a real-time minute-taking system running in on-premise environments
• Generating minutes from meeting audio using local speech recognition models
• Anonymization of unstructured data based on named entity recognition
• Anonymizing personal information by masking names, locations, and addresses in unstructured data

Keywords: RLHF, SFT, Mamba, SSM, MoE

• Acceleration of Transformer mechanisms
• Development of large-scale ETL processes for training data collection
• Distributed training of LLMs
• Visualization of attention between tokens within the language model
• Fine-tuning domain-specific large language models

Question Answering from Large-Scale Unstructured Data using LLM

We used a large-scale language model to build a system of question-answering on large unstructured data without fine-tuning and evaluated its accuracy.

A bottleneck in the application of large-scale language models is the limited number of input tokens. By storing documents in a vector database, which can then be explored and added to the context as required, this problem can be avoided.

Development Environment & Technical Fields: LangChain, LlamaIndex, RAG, Domain Specialization, embeddings, Semantic Search

LLM recursive automated planning systems

We have built an automated planning system for software development by recursively refining the output of a large language model.

Given a software requirement specification as input, this system interactively checks the details of the requirement on the GUI and decomposes it into the tasks required to achieve the goal. The system is actually used in our company.

Development Environment & Technical Fields: Large Language Models, AI Agents