LlamaIndex

Deploy LlamaIndex Agents to Bedrock AgentCore

Deploy LlamaIndex agents to Amazon Bedrock AgentCore Runtime with sandboxed browser and code-execution tools.

Load and Process UniProt Data with LlamaIndex

Parse UniProt Swiss-Prot protein data files into LlamaIndex documents, with lazy loading for multi-GB files.

Augment LLM Agents with Web Search and Extraction

LlamaIndex tool that integrates Parallel AI's Search and Extract APIs to enable LLM agents to perform web research and convert URLs into clean, LLM-optimized

Integrate SERPEX for Real-Time Web Search

LlamaIndex tool that connects AI agents to SERPEX API for real-time web search across Google, Bing, DuckDuckGo, Brave, Yahoo, and Yandex with structured JSON

Securely Ingest Data with Pebblo for LlamaIndex

Wrap any LlamaIndex DocumentReader with Pebblo to surface compliance-relevant topics and entities in loaded data.

Generate Documentation from Code Docstrings

AST-based reader that extracts only docstrings from a code directory into LlamaIndex Documents, avoiding the token cost of feeding full source to an LLM.

Process PDFs with Advanced Layout Preservation

LayoutIR Reader parses complex PDFs into layout-preserving LlamaIndex documents, with GPU acceleration and chunking.

Ingest and Query Semantic Scholar Research Papers

Loads scholarly papers from Semantic Scholar into LlamaIndex Documents for citation-backed research Q&A.

Query Cassandra Data with LLMs

Cassandra Database Tools give an agent safe, read-only access to Cassandra schema and data via optimized queries.

Build a Chatbot with Cohere Citations

A LlamaIndex pack that integrates Cohere's citation-enabled chat API to build conversational search engines with source attribution for every response.

Enhance RAG Retrieval Accuracy with DeepMemory

DeepLake DeepMemory Pack is a LlamaIndex integration for retrieval workflows using DeepLake's DeepMemory vector storage and retrieval capabilities.

Retrieve and Synthesize Multi-Document Insights

Summarize and Retrieve Data with RAPTOR

RAPTOR retrieval LlamaPack that recursively clusters and summarizes documents in layers, offering tree-traversal or collapsed top-k retrieval modes for

Integrate Vectara for RAG and Summarization

End-to-end Retrieval Augmented Generation pack for LlamaIndex using Vectara, with hybrid search, reranking options (MMR, multilingual_reranker_v1, chain), and

Build Voyage AI-powered Query Engine

Voyage Query Engine Pack is a LlamaIndex workflow component that integrates Voyage AI embeddings into query engine pipelines for semantic search and retrieval.

Build Hierarchical Knowledge Graphs for Advanced Retrieval

Two LlamaIndex packs for hierarchical small-to-big retrieval: one for embedded tables via Unstructured.io, one general-purpose recursive retriever.

Query Data with Retry Logic

Retry Query Engine Pack indexes data in Weaviate and retries queries via LlamaIndex's Retry Query Engine for RAG.

Analyze Financial Documents with LlamaIndex

Analyze and compare 10-K financial filings across companies using LlamaIndex's VectorStoreIndex and SubQuestionQueryEngine.