正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

RAG Pipeline: a five-stage retrieval-augmented generation flow, from query to streamed answer with citations. each citation pings its source chunk when it appears in the answer. hover either end and the other lights up in the same hue.

Jeet

6,147 subscribers

30,487 次观看 • 7 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

New short course on advanced retrieval for RAG (retrieval augmented generation)! RAG fetches relevant documents to give context to an LLM. In Advanced Retrieval for AI with Chroma, taught by Chroma founder anton 🇺🇸, you’ll learn: (i) Query expansion using an LLM to rewrite and improve a query, by either generating either additional relevant queries or a hypothetical answer to the query. (ii) Reranking using a cross-encoder - a model trained to measure similarity between two inputs presented simultaneously. Reranking reorders retrieved documents based on the cross-encoder similarity measure. (iii) Constructing and training an Embedding Adaptor, which is a model that adapts the embedding values to be more relevant to your use case. Each of these techniques can help you build much better RAG systems. Please sign up for the course here:

New short course on advanced retrieval for RAG (retrieval augmented generation)! RAG fetches relevant documents to give context to an LLM. In Advanced Retrieval for AI with Chroma, taught by Chroma founder anton 🇺🇸, you’ll learn: (i) Query expansion using an LLM to rewrite and improve a query, by either generating either additional relevant queries or a hypothetical answer to the query. (ii) Reranking using a cross-encoder - a model trained to measure similarity between two inputs presented simultaneously. Reranking reorders retrieved documents based on the cross-encoder similarity measure. (iii) Constructing and training an Embedding Adaptor, which is a model that adapts the embedding values to be more relevant to your use case. Each of these techniques can help you build much better RAG systems. Please sign up for the course here:

Andrew Ng

191,219 次观看 • 2 年前

Build a RAG Application from Scratch 🐕 This video covers the architecture behind Verba 0.3.0! The design behind Verba is to have an explicit manager for each core component of RAG pipelines (Read, Chunk, Embed, Retrieve, Generate) 1. ReaderManager: Load in your data (GitHubReader, PDFReader, SimpleReader, etc.) 2. ChunkManager: Chunk up your data into smaller bits (avoids hitting the token limit and results in better retrieval) 3. EmbeddingManager: Convert your data into embeddings (use OpenAI, Cohere, SentenceTransformer, etc.) 4. RetrieverManager: Retrieve the relevant context from your query 5. GenerationManager: Generate an answer from the retrieved chunks Test out Verba on the Weaviate AI Database docs/blogs here: Verba repo:

Build a RAG Application from Scratch 🐕 This video covers the architecture behind Verba 0.3.0! The design behind Verba is to have an explicit manager for each core component of RAG pipelines (Read, Chunk, Embed, Retrieve, Generate) 1. ReaderManager: Load in your data (GitHubReader, PDFReader, SimpleReader, etc.) 2. ChunkManager: Chunk up your data into smaller bits (avoids hitting the token limit and results in better retrieval) 3. EmbeddingManager: Convert your data into embeddings (use OpenAI, Cohere, SentenceTransformer, etc.) 4. RetrieverManager: Retrieve the relevant context from your query 5. GenerationManager: Generate an answer from the retrieved chunks Test out Verba on the Weaviate AI Database docs/blogs here: Verba repo:

Erika Shorten

155,273 次观看 • 2 年前

Ready to build a “Chat with your code” application with ollama, Weaviate, and LlamaIndex 🦙 on Lightning AI ⚡️ Studio? We’ve just published a Lightning AI Studio template that you can simply copy. You’ll be up and running with your Retrieval-Augmented Generation (RAG) pipeline in minutes. Jump right in here:

Ready to build a “Chat with your code” application with ollama, Weaviate, and LlamaIndex 🦙 on Lightning AI ⚡️ Studio? We’ve just published a Lightning AI Studio template that you can simply copy. You’ll be up and running with your Retrieval-Augmented Generation (RAG) pipeline in minutes. Jump right in here:

Weaviate AI Database

12,435 次观看 • 2 年前

In this short video, I explain the concept of RAG (Retrieval-Augmented Generation) in a simple and easy-to-understand way. I hope it helps! Let me know your thoughts. The material is based on Prof. Tom Yeh's 'AI by Hand' resources.

In this short video, I explain the concept of RAG (Retrieval-Augmented Generation) in a simple and easy-to-understand way. I hope it helps! Let me know your thoughts. The material is based on Prof. Tom Yeh's 'AI by Hand' resources.

Cornelius Adejoro

28,210 次观看 • 1 年前

New short course on sophisticated RAG (Retrieval Augmented Generation) techniques is out! Taught by Jerry Liu and Anupam Datta of LlamaIndex 🦙 and TruEra , this teaches advanced techniques that help your LLM generate good answers. Topics include: - Sentence-window retrieval, which retrieves not just the most relevant sentence, but a window of sentences around it for higher quality context. - Auto-merging retrieval, which organizes your document into a hierarchical tree structure, where each parent node's text is split among its child nodes. Based on the relevance of the child nodes to a user query, this lets you better decide whether the entire parent node should be provided as context to the LLM. - Evaluation methodology for separately evaluating the quality of the key steps of RAG (context relevance, answer relevance, groundedness) so that you can perform error analysis, identify which part of your pipeline needs work, and tune components systematically. Please check out the course!

New short course on sophisticated RAG (Retrieval Augmented Generation) techniques is out! Taught by Jerry Liu and Anupam Datta of LlamaIndex 🦙 and TruEra , this teaches advanced techniques that help your LLM generate good answers. Topics include: - Sentence-window retrieval, which retrieves not just the most relevant sentence, but a window of sentences around it for higher quality context. - Auto-merging retrieval, which organizes your document into a hierarchical tree structure, where each parent node's text is split among its child nodes. Based on the relevance of the child nodes to a user query, this lets you better decide whether the entire parent node should be provided as context to the LLM. - Evaluation methodology for separately evaluating the quality of the key steps of RAG (context relevance, answer relevance, groundedness) so that you can perform error analysis, identify which part of your pipeline needs work, and tune components systematically. Please check out the course!

Andrew Ng

655,661 次观看 • 2 年前

Verba is an open source Retrieval Augmented Generation (RAG) application that performs RAG on your own data. To showcase its capabilities, we've customized it as an Airbnb chatbot using Airbnb’s customer documentation. How it works: • Ask any questions, related to your booking, policies, or anything related to your Airbnb experience. • Get relevant, human-like responses: Verba provides natural and informative answers. • Access original sources: One of the standout features of RAG is its ability to directly indicate the sources it used to generate each response. Under the hood, Verba uses a RAG pipeline to deliver these exceptional results. Your query is transformed into a numerical representation (vector) and be used to search through our vector database for the most similar context using Hybrid Search. The most relevant context is then combined with your original question and fed into a powerful large language model (LLM). The LLM will then use all of that information to generate a conversational response. Et voilà! 💫 Try Verba: Verba on GitHub: Learn more in our video:

Verba is an open source Retrieval Augmented Generation (RAG) application that performs RAG on your own data. To showcase its capabilities, we've customized it as an Airbnb chatbot using Airbnb’s customer documentation. How it works: • Ask any questions, related to your booking, policies, or anything related to your Airbnb experience. • Get relevant, human-like responses: Verba provides natural and informative answers. • Access original sources: One of the standout features of RAG is its ability to directly indicate the sources it used to generate each response. Under the hood, Verba uses a RAG pipeline to deliver these exceptional results. Your query is transformed into a numerical representation (vector) and be used to search through our vector database for the most similar context using Hybrid Search. The most relevant context is then combined with your original question and fed into a powerful large language model (LLM). The LLM will then use all of that information to generate a conversational response. Et voilà! 💫 Try Verba: Verba on GitHub: Learn more in our video:

Femke Plantinga

120,565 次观看 • 2 年前

Announcing a new Coursera course: Retrieval Augmented Generation (RAG) You'll learn to build high performance, production-ready RAG systems in this hands-on, in-depth course created by and taught by , experienced AI and ML engineer, researcher, and educator. RAG is a critical component today of many LLM-based applications in customer support, internal company Q&A systems, even many of the leading chatbots that use web search to answer your questions. This course teaches you in-depth how to make RAG work well. LLMs can produce generic or outdated responses, especially when asked specialized questions not covered in its training data. RAG is the most widely used technique for addressing this. It brings in data from new data sources, such as internal documents or recent news, to give the LLM the relevant context to private, recent, or specialized information. This lets it generate more grounded and accurate responses. In this course, you’ll learn to design and implement every part of a RAG system, from retrievers to vector databases to generation to evals. You’ll learn about the fundamental principles behind RAG and how to optimize it at both the component and whole-system levels. As AI evolves, RAG is evolving too. New models can handle longer context windows, reason more effectively, and can be parts of complex agentic workflows. One exciting growth area is Agentic RAG, in which an AI agent at runtime (rather than it being hardcoded at development time) autonomously decides what data to retrieve, and when/how to go deeper. Even with this evolution, access to high-quality data at runtime is essential, which is why RAG is a key part of so many applications. You'll learn via hands-on experiences to: - Build a RAG system with retrieval and prompt augmentation - Compare retrieval methods like BM25, semantic search, and Reciprocal Rank Fusion - Chunk, index, and retrieve documents using a Weaviate vector database and a news dataset - Develop a chatbot, using open-source LLMs hosted by Together AI, for a fictional store that answers product and FAQ questions - Use evals to drive improving reliability, and incorporate multi-modal data RAG is an important foundational technique. Become good at it through this course! Please sign up here:

Announcing a new Coursera course: Retrieval Augmented Generation (RAG) You'll learn to build high performance, production-ready RAG systems in this hands-on, in-depth course created by and taught by , experienced AI and ML engineer, researcher, and educator. RAG is a critical component today of many LLM-based applications in customer support, internal company Q&A systems, even many of the leading chatbots that use web search to answer your questions. This course teaches you in-depth how to make RAG work well. LLMs can produce generic or outdated responses, especially when asked specialized questions not covered in its training data. RAG is the most widely used technique for addressing this. It brings in data from new data sources, such as internal documents or recent news, to give the LLM the relevant context to private, recent, or specialized information. This lets it generate more grounded and accurate responses. In this course, you’ll learn to design and implement every part of a RAG system, from retrievers to vector databases to generation to evals. You’ll learn about the fundamental principles behind RAG and how to optimize it at both the component and whole-system levels. As AI evolves, RAG is evolving too. New models can handle longer context windows, reason more effectively, and can be parts of complex agentic workflows. One exciting growth area is Agentic RAG, in which an AI agent at runtime (rather than it being hardcoded at development time) autonomously decides what data to retrieve, and when/how to go deeper. Even with this evolution, access to high-quality data at runtime is essential, which is why RAG is a key part of so many applications. You'll learn via hands-on experiences to: - Build a RAG system with retrieval and prompt augmentation - Compare retrieval methods like BM25, semantic search, and Reciprocal Rank Fusion - Chunk, index, and retrieve documents using a Weaviate vector database and a news dataset - Develop a chatbot, using open-source LLMs hosted by Together AI, for a fictional store that answers product and FAQ questions - Use evals to drive improving reliability, and incorporate multi-modal data RAG is an important foundational technique. Become good at it through this course! Please sign up here:

Andrew Ng

124,656 次观看 • 1 年前

A quick introduction for those who'd like a 𝗿𝗲𝗳𝗿𝗲𝘀𝗵𝗲𝗿 𝗼𝗻 𝗥𝗔𝗚 or missed THE 2024 AI hype 😆 (Since 2024 isn't over yet, I'll take my chance to explain it) Mary wrote this amazing introductory blog post for Weaviate AI Database, and I thought, why not make a video about it? 🤔 Let’s go over the basics: • What is Retrieval Augmented Generation (RAG) • Why do we need RAG? • Example of a naive RAG pipeline • Complications of RAG Check out her blog to get the full picture:

A quick introduction for those who'd like a 𝗿𝗲𝗳𝗿𝗲𝘀𝗵𝗲𝗿 𝗼𝗻 𝗥𝗔𝗚 or missed THE 2024 AI hype 😆 (Since 2024 isn't over yet, I'll take my chance to explain it) Mary wrote this amazing introductory blog post for Weaviate AI Database, and I thought, why not make a video about it? 🤔 Let’s go over the basics: • What is Retrieval Augmented Generation (RAG) • Why do we need RAG? • Example of a naive RAG pipeline • Complications of RAG Check out her blog to get the full picture:

Femke Plantinga

20,558 次观看 • 1 年前

MICROSOFT QUIETLY SHIPPED THE RAG PIPELINE EVERYONE KEEPS TRYING TO BUILD FROM SCRATCH it is called Kernel Memory, and it turns any pile of files into an AI memory that answers with citations. drop your data in and Microsoft's pipeline does the rest: > ingest PDFs, Word, PPT, Excel, web pages, even images > extract the text, chunk it, embed it into vectors > store the vectors with metadata and keep the originals in blob storage > ask a question and it pulls the right chunks with semantic plus hybrid search then it hands the answer back grounded, with links to the exact source and full token usage. and it plugs into whatever you already run: > Azure OpenAI, OpenAI, Ollama, or Anthropic for the models > Qdrant, pgvector, Redis, or Azure AI Search for the vectors > every step is a swappable handler, so you can replace any part with your own one heads up: Microsoft archived the repo in June 2026 and ships it as a reference blueprint, not production. but as a map for how memory and RAG are actually built, nothing is cleaner. run it in one command: docker run kernelmemory/service bookmark this. Microsoft already drew the blueprint, you just build on it.

MICROSOFT QUIETLY SHIPPED THE RAG PIPELINE EVERYONE KEEPS TRYING TO BUILD FROM SCRATCH it is called Kernel Memory, and it turns any pile of files into an AI memory that answers with citations. drop your data in and Microsoft's pipeline does the rest: > ingest PDFs, Word, PPT, Excel, web pages, even images > extract the text, chunk it, embed it into vectors > store the vectors with metadata and keep the originals in blob storage > ask a question and it pulls the right chunks with semantic plus hybrid search then it hands the answer back grounded, with links to the exact source and full token usage. and it plugs into whatever you already run: > Azure OpenAI, OpenAI, Ollama, or Anthropic for the models > Qdrant, pgvector, Redis, or Azure AI Search for the vectors > every step is a swappable handler, so you can replace any part with your own one heads up: Microsoft archived the repo in June 2026 and ships it as a reference blueprint, not production. but as a map for how memory and RAG are actually built, nothing is cleaner. run it in one command: docker run kernelmemory/service bookmark this. Microsoft already drew the blueprint, you just build on it.

NO1ennn

85,010 次观看 • 21 天前

STANFORD BUILT AN LLM MEMORY THAT WORKS LIKE A BRAIN AND IT MADE STANDARD RAG LOOK ANCIENT no fine-tuning. no bigger model. just a smarter way to remember the insight: the brain doesn't store memories as isolated notes. it indexes them and links them - so one cue pulls back the whole memory so HippoRAG stops treating documents as separate chunks. it builds a knowledge graph, then spreads activation across it (Personalized PageRank) to pull a full answer from a single cue - the brain calls this "pattern completion" the result: > up to 20% better on hard multi-hop questions > 10-30x cheaper and 6-13x faster than iterative retrieval > connects facts split across documents in a single step most RAG still encodes every passage in isolation - so it breaks the moment the answer is scattered more retrieval was never the answer. brain-like memory is bookmark this. the next leap in AI agents is how they remember, not how big they get

STANFORD BUILT AN LLM MEMORY THAT WORKS LIKE A BRAIN AND IT MADE STANDARD RAG LOOK ANCIENT no fine-tuning. no bigger model. just a smarter way to remember the insight: the brain doesn't store memories as isolated notes. it indexes them and links them - so one cue pulls back the whole memory so HippoRAG stops treating documents as separate chunks. it builds a knowledge graph, then spreads activation across it (Personalized PageRank) to pull a full answer from a single cue - the brain calls this "pattern completion" the result: > up to 20% better on hard multi-hop questions > 10-30x cheaper and 6-13x faster than iterative retrieval > connects facts split across documents in a single step most RAG still encodes every passage in isolation - so it breaks the moment the answer is scattered more retrieval was never the answer. brain-like memory is bookmark this. the next leap in AI agents is how they remember, not how big they get

NO1ennn

32,454 次观看 • 1 个月前

GIBRALTAR In answer to my question, it is clear from the Foreign Secretary’s answer that Spanish border officials can prevent a UK citizen from entering one part of the UK from another part of the UK. This appears to be a significant sovereign compromise.

GIBRALTAR In answer to my question, it is clear from the Foreign Secretary’s answer that Spanish border officials can prevent a UK citizen from entering one part of the UK from another part of the UK. This appears to be a significant sovereign compromise.

Richard Tice MP 🇬🇧

83,722 次观看 • 1 年前

We're unlocking next-level AI capabilities with the launch of our Retrieval Augmentation Generation (RAG) architecture! 🌟 By integrating a sophisticated information retrieval system, RAG empowers our Large Language Model (LLM), Qwen, with an extra layer of context, allowing it to access industry-specific insights or a company's proprietary data on demand. At the heart of RAG's knowledgebase lies the Vector Engine – a powerhouse of semantic recall ensuring all data is meticulously preserved and readily accessible. Plus, with Alibaba Cloud's suite of vector database solutions, we're at the forefront of augmented data retrieval, offering unprecedented precision and speed. Get ready to transform your data strategy with RAG! #AlibabaCloud #AI #Innovation #DataStrategy #VectorEngine #RAG #AIandBigDataSummit2024 #AIForward

We're unlocking next-level AI capabilities with the launch of our Retrieval Augmentation Generation (RAG) architecture! 🌟 By integrating a sophisticated information retrieval system, RAG empowers our Large Language Model (LLM), Qwen, with an extra layer of context, allowing it to access industry-specific insights or a company's proprietary data on demand. At the heart of RAG's knowledgebase lies the Vector Engine – a powerhouse of semantic recall ensuring all data is meticulously preserved and readily accessible. Plus, with Alibaba Cloud's suite of vector database solutions, we're at the forefront of augmented data retrieval, offering unprecedented precision and speed. Get ready to transform your data strategy with RAG! #AlibabaCloud #AI #Innovation #DataStrategy #VectorEngine #RAG #AIandBigDataSummit2024 #AIForward

Alibaba Cloud

9,636,416 次观看 • 2 年前

Imagine stepping into your embeddings that power RAG. 📚 In this proof of concept, you’re surrounded by courses. Semantically similar ones float right next to each other. I've built an XR prototype with Rémi at In The Pocket where you can stand inside your knowledge base on Apple Vision Pro. Ask a question and the AI lights up the relevant documents in space, so you literally see where your answer comes from. When you ask something specific like "I want to be an astronaut, what can I learn", only a few tight clusters glow. But ask "I'm bored, what could be something fun to study" and clusters across the space light up. #applevisionpro #artificialintelligence #xr #rag

Imagine stepping into your embeddings that power RAG. 📚 In this proof of concept, you’re surrounded by courses. Semantically similar ones float right next to each other. I've built an XR prototype with Rémi at In The Pocket where you can stand inside your knowledge base on Apple Vision Pro. Ask a question and the AI lights up the relevant documents in space, so you literally see where your answer comes from. When you ask something specific like "I want to be an astronaut, what can I learn", only a few tight clusters glow. But ask "I'm bored, what could be something fun to study" and clusters across the space light up. #applevisionpro #artificialintelligence #xr #rag

Stijn Spanhove

24,747 次观看 • 6 个月前

Palestine Solidarity Youth Campaign catches up with Connie Chan. Look how easy it is for her to answer these questions. And compare to Scott Wiener at the end squirming with the same ones.

Palestine Solidarity Youth Campaign catches up with Connie Chan. Look how easy it is for her to answer these questions. And compare to Scott Wiener at the end squirming with the same ones.

Y Disassembler

20,283 次观看 • 23 天前

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Santiago

40,627 次观看 • 1 年前

Let's build a dashboard to evaluate and monitor your Agentic and RAG apps! . . In this video, I'll guide you through creating an evaluation and observability pipeline for your AI apps using a 100% open-source tool! Tech Stack: - Comet's Opik to eval and monitor - LlamaIndex to build a RAG pipeline - Ragas for synthetic datagen You'll learn: - Setting up Opik - Building a RAG pipeline - Creating an eval dataset - Evaluating the RAG pipeline - Monitoring all activities during the process It's a hands on demo with code and step-by-step guide to do everything listed above. CometML's Opik is fully open-source, offering the most Pythonic and easiest way to monitor LLM apps. I have shared link to their repo in next tweet!

Let's build a dashboard to evaluate and monitor your Agentic and RAG apps! . . In this video, I'll guide you through creating an evaluation and observability pipeline for your AI apps using a 100% open-source tool! Tech Stack: - Comet's Opik to eval and monitor - LlamaIndex to build a RAG pipeline - Ragas for synthetic datagen You'll learn: - Setting up Opik - Building a RAG pipeline - Creating an eval dataset - Evaluating the RAG pipeline - Monitoring all activities during the process It's a hands on demo with code and step-by-step guide to do everything listed above. CometML's Opik is fully open-source, offering the most Pythonic and easiest way to monitor LLM apps. I have shared link to their repo in next tweet!

Akshay 🚀

20,058 次观看 • 1 年前

From investing in Indian operations to creating multiple job opportunities, vivo has positively impacted Indians with each of its achievements and will continue the same in the future. (Source: vivo India Impact Report 2023).

From investing in Indian operations to creating multiple job opportunities, vivo has positively impacted Indians with each of its achievements and will continue the same in the future. (Source: vivo India Impact Report 2023).

vivo India

25,389,967 次观看 • 2 年前