20250201AI应用相关技术调研

背景

20230515LLM笔记

继上次调研后,很久没更新AI相关技术了,这次一并更新。

应用框架

数据索引框架 data index framework

llamaindex

https://docs.llamaindex.ai/en/stable/ https://github.com/run-llama/llama_index

https://docs.llamaindex.ai/en/stable/use_cases/agents/ Property Graph Index可以用neo4j

https://docs.llamaindex.ai/en/stable/module_guides/storing Vector Stores:Elasticsearch、Lantern、OpenSearch、Postgres、Qdrant Document Stores:Mongo、Redis Index Stores:Mongo、Redis Chat Stores:Redis Key-Value Stores:Mongo Note: At the moment, these storage abstractions are not externally facing. https://docs.llamaindex.ai/en/stable/module_guides/storing/customization/

ai agents framework

自动化框架 restack

https://www.restack.io/

agents框架 eko

https://github.com/FellouAI/eko

pydantic

https://github.com/pydantic/pydantic-ai

composio

https://composio.dev/swe-kit/ https://github.com/ComposioHQ/composio/tree/master/python/swe?utm_source=website https://docs.composio.dev/framework/llamaindex https://docs.composio.dev/framework/langchain

prompt框架

https://docs.langchain4j.dev/ https://github.com/langchain4j/langchain4j

https://docs.spring.io/spring-ai/reference/index.html https://github.com/spring-projects/spring-ai xinference

AI上下文协议框架MCP

https://modelcontextprotocol.io/introduction https://modelcontextprotocol.io/quickstart https://github.com/modelcontextprotocol https://github.com/modelcontextprotocol/servers

向量数据库

https://lancedb.github.io/lancedb/concepts/storage/ embeddedable|localfile|s3

https://www.trychroma.com/ embeddedable|localfile

https://milvus.io/ need etcd、Pulsar embeddedable|s3

es dense_vector

0 Comments
Leave a Reply