LLM / Runtime
•
Ollama
•
gpt-oss
•
Local LLM
•
Open Source LLM
RAG Core
•
RAG
•
RAG Pipeline
•
Retrieval-Augmented Generation
•
PromptTemplate
•
Context Injection
Framework / Tooling
•
LangChain
•
LangSmith
•
Chain
•
Runnable
•
Callback
•
Tracing
Model / API
•
ChatOpenAI
•
OpenAI API
•
API Key
•
API Quota
•
Rate Limit
•
ChatUpstage
Embedding
•
OpenAIEmbeddings
•
UpstageEmbeddings
•
Text Embedding
•
Vectorization
Vector Store / DB
•
Chroma
•
Pinecone
•
Vector Store
•
Vector DB
•
Similarity Search
•
Metadata Filter
•
Hybrid Search
RAG Optimization
•
Chunking
•
Chunk Size
•
Overlap
•
Retrieval
•
Top-K
•
Re-ranking
•
Score Threshold
LangChain-less RAG
•
Custom Pipeline
•
Direct SDK
•
REST API
•
Embedding + Search + LLM
Workflow / Automation
•
n8n
•
Webhook
•
Scheduler
•
Trigger
•
Automation Pipeline
안녕하세요
•
관련 기술 문의와 R&D 공동 연구 사업 관련 문의는 “glory@keti.re.kr”로 연락 부탁드립니다.
Hello
•
For technical and business inquiries, please contact me at “glory@keti.re.kr”