Multi-step prompt sequences for complex AI workflows.
11 tools found
A LlamaIndex notebook workflow that builds and evaluates Retrieval Augmented Generation (RAG) pipelines using hit rate, MRR, faithfulness, and relevancy
Analyze 10-K financial documents with LlamaIndex. Extract insights and synthesize information across multiple reports.
LlamaIndex pack that creates a Cohere-powered chat engine with document citations for retrieval-augmented generation.
A LlamaIndex pack that inserts data into DeepLake and instantiates a DeepMemory retriever for RAG applications.
LLaVA Completion Pack is a LlamaIndex LlamaPack that creates a multimodal LLaVA model instance and runs its complete endpoint to execute queries.
A LlamaPack that implements structured hierarchical retrieval over multiple documents using Weaviate collections.
RAPTOR retrieval LlamaPack that recursively clusters and summarizes documents in layers, offering tree-traversal or collapsed top-k retrieval modes for
LlamaIndex LlamaPacks for recursive retrieval with hierarchical node graphs, providing two templates: EmbeddedTablesUnstructuredRetrieverPack and
LlamaPack that inserts data into Weaviate and uses the Retry Query Engine for RAG applications.
End-to-end Retrieval Augmented Generation pack for LlamaIndex using Vectara, with hybrid search, reranking options (MMR, multilingual_reranker_v1, chain), and
Create a query engine using GPT4 and Voyage AI Embeddings.
