LLM# Completion Pipeline Table of Contents Supported Environments Background Information Purpose LLM Service Downstream Tasks Pipeline Implementation Getting Started Prerequisites Install Dependencies Running the Morpheus Pipeline Run example: Commands: Options: Running Morpheus Pipeline with OpenAI LLM service Vector DataBase Upload (VDB Upload) Pipeline Table of Contents Supported Environments Supported Architectures Background Information Purpose Source Documents Embedding Model Vector Database Service Implementation and Design Decisions Implementation Details Rationale Behind Design Decisions Getting Started Prerequisites Ensure LFS files are downloaded Milvus Service Triton Service Running the Morpheus Pipeline Configuration Balance Considerations Run example: Options for vdb_upload Command Commands: Exporting and Deploying a Different Model from Hugging Face Running the LangChain Pipeline (Optional) Retrieval Augmented Generation (RAG) Pipeline Supported Environments Supported Architectures Table of Contents Background Information Purpose Source Documents Vector Database Service Implementation and Design Decisions Implementation Details Rationale Behind Design Decisions Standalone Morpheus Pipeline Prerequisites Obtain an NVIDIA API key Milvus Service Running the Morpheus Pipeline Run example (Standalone Pipeline): Morpheus LLM Agents Pipeline Table of Contents Supported Environments Background Information Purpose LLM Service Agent type Agent tools LLM Library Pipeline Implementation Getting Started Prerequisites Set Environment Variables Install Dependencies Running the Morpheus Pipeline Run example (Simple Pipeline): Options: Run example (Kafka Pipeline): Options:
