From 7297eeaa6ee1cc0959940170fd682ed942839637 Mon Sep 17 00:00:00 2001 From: tryptofanik <49122854+tryptofanik@users.noreply.github.com> Date: Thu, 16 Jan 2025 15:59:05 +0100 Subject: [PATCH] New data indexing docs page (#8013) GitOrigin-RevId: d4af088f50bb592678fe5fd782139c1b938495da --- examples/pipelines/demo-question-answering/README.md | 2 +- examples/pipelines/gpt_4o_multimodal_rag/README.md | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/examples/pipelines/demo-question-answering/README.md b/examples/pipelines/demo-question-answering/README.md index 2e485f5..0824be0 100644 --- a/examples/pipelines/demo-question-answering/README.md +++ b/examples/pipelines/demo-question-answering/README.md @@ -28,7 +28,7 @@ This demo allows you to: - Get an executive outlook for a question on different files to easily access available knowledge in your documents; -Note: This app relies on [Pathway Vector store](https://pathway.com/developers/api-docs/pathway-xpacks-llm/vectorstore) to learn more, you can check out [this blog post](https://pathway.com/developers/user-guide/llm-xpack/vectorstore_pipeline/). +Note: This app relies on [Document Store](https://pathway.com/developers/api-docs/pathway-xpacks-llm/document_store) to learn more, you can check out [this blog post](https://pathway.com/developers/user-guide/llm-xpack/docs-indexing/). ## Table of contents - [Summary of available endpoints](#Summary-of-available-endpoints) diff --git a/examples/pipelines/gpt_4o_multimodal_rag/README.md b/examples/pipelines/gpt_4o_multimodal_rag/README.md index bbbd1b3..223b0e1 100644 --- a/examples/pipelines/gpt_4o_multimodal_rag/README.md +++ b/examples/pipelines/gpt_4o_multimodal_rag/README.md @@ -51,7 +51,7 @@ The architecture of this multimodal RAG application involves several key compone - **Data Ingestion**: Ingests data from various sources like local folders, Google Drive, or SharePoint. - **Document Parsing and Embedding**: Utilizes `OpenParse` for parsing documents and `OpenAIEmbedder` for embedding text. This includes handling and processing images within PDFs. -- **Vector Store**: The `VectorStoreServer` indexes parsed documents and retrieves relevant chunks for answering questions. +- **Document Store**: The `DocumentStoreServer` indexes parsed documents and retrieves relevant chunks for answering questions. - **Question Answering**: Uses the `BaseRAGQuestionAnswerer` class to call `GPT-4o` for generating responses based on the retrieved context. - **Server Setup**: Sets up a REST endpoint to serve the RAG application. @@ -266,7 +266,6 @@ Let's discuss how we can help you build a powerful, customized RAG application. - [Discord Community of Pathway](https://discord.gg/pathway) - [Pathway Issue Tracker](https://github.com/pathwaycom/pathway/issues) - [End-to-end dynamic RAG pipeline with Pathway](https://github.com/pathwaycom/llm-app/tree/main/examples/pipelines/demo-question-answering) -- [Using Pathway as a vector store with Langchain](https://python.langchain.com/v0.2/docs/integrations/vectorstores/pathway/) - [Using Pathway as a retriever with LlamaIndex](https://docs.llamaindex.ai/en/stable/examples/retrievers/pathway_retriever/) Make sure to drop a "Star" to our repositories if you found this resource helpful!