Fix duplicate Infinity naming in RAG section

Clarify two different projects:
- Infinity (Embeddings Server) - michaelfeil/infinity - text-embeddings serving
- Infinity (AI Database) - infiniflow/infinity - AI-native vector database

Resolves CI validation failure caused by ambiguous duplicate naming.

Author: alvinreal

README.md

@@ -496,7 +496,7 @@
 - **[LangChain4j](https://github.com/langchain4j/langchain4j)** ![GitHub stars](https://img.shields.io/github/stars/langchain4j/langchain4j?style=social) - Java library for integrating LLMs into Java applications. Implements RAG, tool calling (including MCP support), and agents with seamless integration into enterprise Java frameworks like Spring Boot. Apache 2.0 licensed.
 - **[Kernel Memory (Microsoft)](https://github.com/microsoft/kernel-memory)** ![GitHub stars](https://img.shields.io/github/stars/microsoft/kernel-memory?style=social) - Memory solution for users, teams, and applications. RAG pipelines with document ingestion, vector indexing, and natural language querying with citations. Supports multiple LLM providers and vector stores. MIT licensed.
 - **[txtai](https://github.com/neuml/txtai)** ![GitHub stars](https://img.shields.io/github/stars/neuml/txtai?style=social) - All-in-one AI framework for semantic search, LLM orchestration and language model workflows. Embeddings database with customizable pipelines.
-- **[Infinity](https://github.com/michaelfeil/infinity)** ![GitHub stars](https://img.shields.io/github/stars/michaelfeil/infinity?style=social) - High-throughput, low-latency serving engine for text-embeddings, reranking, CLIP, and ColPali. OpenAI-compatible API.
+- **[Infinity (Embeddings Server)](https://github.com/michaelfeil/infinity)** ![GitHub stars](https://img.shields.io/github/stars/michaelfeil/infinity?style=social) - High-throughput, low-latency serving engine for text-embeddings, reranking, CLIP, and ColPali. OpenAI-compatible API.
 - **[FlashRAG](https://github.com/RUC-NLPIR/FlashRAG)** ![GitHub stars](https://img.shields.io/github/stars/RUC-NLPIR/FlashRAG?style=social) - Efficient toolkit for RAG research with 40+ retrieval and reranking models, 20+ benchmark datasets, and optimized evaluation pipelines (WWW 2025 Resource). MIT licensed.
 - **[DocsGPT](https://github.com/arc53/DocsGPT)** ![GitHub stars](https://img.shields.io/github/stars/arc53/DocsGPT?style=social) - Private AI platform for building intelligent agents and assistants with enterprise search. Features Agent Builder, deep research tools, multi-format document analysis, and multi-model support. MIT licensed.
 - **[llmware](https://github.com/llmware-ai/llmware)** ![GitHub stars](https://img.shields.io/github/stars/llmware-ai/llmware?style=social) - Unified framework for building enterprise RAG pipelines with small, specialized models. Optimized for AI PC and local deployment with 300+ models in catalog. Apache 2.0 licensed.
@@ -513,7 +513,7 @@
 - **[Quivr](https://github.com/QuivrHQ/quivr)** ![GitHub stars](https://img.shields.io/github/stars/QuivrHQ/quivr?style=social) - Opinionated RAG framework for building your "second brain" - a personal productivity assistant that lets you chat with your documents. Works with any LLM and vector store. Easy integration into existing products with customization options. Apache 2.0 licensed.
 - **[Vanna](https://github.com/vanna-ai/vanna)** ![GitHub stars](https://img.shields.io/github/stars/vanna-ai/vanna?style=social) - RAG-based text-to-SQL generation with agentic retrieval. Chat with your SQL database using natural language. Features user-aware permissions, enterprise security, and a modern web interface with streaming responses. MIT licensed.
 - **[Pathway](https://github.com/pathwaycom/pathway)** ![GitHub stars](https://img.shields.io/github/stars/pathwaycom/pathway?style=social) - Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG. Features 350+ connectors with always-in-sync data from SharePoint, Google Drive, S3, Kafka, PostgreSQL and more. BSL 1.1 license (becomes Apache 2.0 after 4 years).
-- **[Infinity](https://github.com/infiniflow/infinity)** ![GitHub stars](https://img.shields.io/github/stars/infiniflow/infinity?style=social) - AI-native database built for LLM applications with incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text. Powers RAGFlow's document engine. Apache 2.0 licensed.
+- **[Infinity (AI Database)](https://github.com/infiniflow/infinity)** ![GitHub stars](https://img.shields.io/github/stars/infiniflow/infinity?style=social) - AI-native database built for LLM applications with incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text. Powers RAGFlow's document engine. Apache 2.0 licensed.
 
 #### Knowledge Graphs for RAG