Skip to main content
LlamaIndex

LlamaIndex

Build RAG applications using the LlamaIndex API

Alibaba Cloud Bailian supports building Retrieval-Augmented Generation (RAG) applications via the LlamaIndex API—ideal for private-knowledge Q&A, customer support, and similar use cases. In this solution, LlamaIndex provides tooling and frameworks for building RAG applications, while Alibaba Cloud Bailian delivers data management capabilities and large language model (LLM) services.
This solution deploys knowledge bases in the cloud and uses the default intelligent document chunking logic along with the official vector embedding model. Custom document chunking strategies or custom embedding models are not supported.

Component List

ComponentDescription
Embedding ModelUses Bailian’s Embedding model
DashScopeRerankRe-ranking component
DashScopeJsonNodeParserJSON node parser
DashScopeCloudRetrieverCloud-based knowledge base retriever
Cloud Knowledge Base ServiceLeverages Alibaba Cloud Bailian’s cloud knowledge base and indexing services
Document ParsingIntelligent document parsing and chunking

Solution Overview

  1. Upload and manage documents using Bailian’s data management features
  2. Retrieve relevant content via LlamaIndex’s DashScopeCloudRetriever
  3. Generate responses using Bailian’s large language models

Installation

pip install llama-index-indices-managed-dashscope
pip install llama-index-embeddings-dashscope
pip install llama-index-postprocessor-dashscope-rerank
Overview
Managed Agent API
Sandbox API
Memory API
Flow Agent API
RAG API
Connector API
Assistant API (Deprecating)
  • Overview