From a2700b301de4205b5c604e3644baa79ed039060c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Iv=C3=A1n=20Mart=C3=ADnez?= Date: Thu, 19 Oct 2023 15:28:37 +0200 Subject: [PATCH] Update twitter link. --- README.md | 84 +++++++++++++++++++++++++++---------------------------- 1 file changed, 42 insertions(+), 42 deletions(-) diff --git a/README.md b/README.md index f8593fee3..a61a40633 100644 --- a/README.md +++ b/README.md @@ -2,11 +2,11 @@ demo -PrivateGPT is a production-ready AI project that allows you to ask questions to your documents using the power -of Large Language Models (LLMs), even in scenarios without Internet connection. 100% private, no data leaves your +PrivateGPT is a production-ready AI project that allows you to ask questions to your documents using the power +of Large Language Models (LLMs), even in scenarios without Internet connection. 100% private, no data leaves your execution environment at any point. -The project provides an API offering all the primitives required to build private, context-aware AI applications. +The project provides an API offering all the primitives required to build private, context-aware AI applications. It follows and extends [OpenAI API standard](https://openai.com/blog/openai-api), and supports both normal and streaming responses. @@ -14,56 +14,56 @@ The API is divided into two logical blocks: **High-level API**, which abstracts all the complexity of a RAG (Retrieval Augmented Generation) pipeline implementation: -- Ingestion of documents: internally managing document parsing, +- Ingestion of documents: internally managing document parsing, splitting, metadata extraction, embedding generation and storage. -- Chat & Completions using context from ingested documents: +- Chat & Completions using context from ingested documents: abstracting the retrieval of context, the prompt engineering and the response generation. **Low-level API**, which allows advanced users to implement their own complex pipelines: - Embeddings generation: based on a piece of text. - Contextual chunks retrieval: given a query, returns the most relevant chunks of text from the ingested documents. -In addition to this, a working [Gradio UI](https://www.gradio.app/) +In addition to this, a working [Gradio UI](https://www.gradio.app/) client is provided to test the API, together with a set of useful tools such as bulk model download script, ingestion script, documents folder watch, etc. -> 👂 **Need help applying PrivateGPT to your specific use case?** -> [Let us know more about it](https://forms.gle/4cSDmH13RZBHV9at7) +> 👂 **Need help applying PrivateGPT to your specific use case?** +> [Let us know more about it](https://forms.gle/4cSDmH13RZBHV9at7) > and we'll try to help! We are refining PrivateGPT through your feedback. ## 🎞️ Overview -DISCLAIMER: This README is not updated as frequently as the [documentation](https://docs.privategpt.dev/). +DISCLAIMER: This README is not updated as frequently as the [documentation](https://docs.privategpt.dev/). Please check it out for the latest updates! ### Motivation behind PrivateGPT Generative AI is a game changer for our society, but adoption in companies of all size and data-sensitive -domains like healthcare or legal is limited by a clear concern: **privacy**. -Not being able to ensure that your data is fully under your control when using third-party AI tools +domains like healthcare or legal is limited by a clear concern: **privacy**. +Not being able to ensure that your data is fully under your control when using third-party AI tools is a risk those industries cannot take. ### Primordial version -The first version of PrivateGPT was launched in May 2023 as a novel approach to address the privacy -concern by using LLMs in a complete offline way. +The first version of PrivateGPT was launched in May 2023 as a novel approach to address the privacy +concern by using LLMs in a complete offline way. This was done by leveraging existing technologies developed by the thriving Open Source AI community: -[LangChain](https://github.com/hwchase17/langchain), [LlamaIndex](https://www.llamaindex.ai/), -[GPT4All](https://github.com/nomic-ai/gpt4all), -[LlamaCpp](https://github.com/ggerganov/llama.cpp), -[Chroma](https://www.trychroma.com/) +[LangChain](https://github.com/hwchase17/langchain), [LlamaIndex](https://www.llamaindex.ai/), +[GPT4All](https://github.com/nomic-ai/gpt4all), +[LlamaCpp](https://github.com/ggerganov/llama.cpp), +[Chroma](https://www.trychroma.com/) and [SentenceTransformers](https://www.sbert.net/). That version, which rapidly became a go-to project for privacy-sensitive setups and served as the seed -for thousands of local-focused generative AI projects, was the foundation of what PrivateGPT is becoming nowadays; -thus a simpler and more educational implementation to understand the basic concepts required +for thousands of local-focused generative AI projects, was the foundation of what PrivateGPT is becoming nowadays; +thus a simpler and more educational implementation to understand the basic concepts required to build a fully local -and therefore, private- chatGPT-like tool. -If you want to keep experimenting with it, we have saved it in the +If you want to keep experimenting with it, we have saved it in the [primordial branch](https://github.com/imartinez/privateGPT/branches) of the project. ### Present and Future of PrivateGPT -PrivateGPT is now evolving towards becoming a gateway to generative AI models and primitives, including -completions, document ingestion, RAG pipelines and other low-level building blocks. +PrivateGPT is now evolving towards becoming a gateway to generative AI models and primitives, including +completions, document ingestion, RAG pipelines and other low-level building blocks. We want to make easier for any developer to build AI applications and experiences, as well as providing -a suitable extensive architecture for the community to keep contributing. +a suitable extensive architecture for the community to keep contributing. Stay tuned to our [releases](https://github.com/imartinez/privateGPT/releases) to check all the new features and changes included. @@ -72,31 +72,31 @@ Full documentation on installation, dependencies, configuration, running the ser ingesting local documents, API details and UI features can be found here: https://docs.privategpt.dev/ ## 🧩 Architecture -Conceptually, PrivateGPT is an API that wraps a RAG pipeline and exposes its +Conceptually, PrivateGPT is an API that wraps a RAG pipeline and exposes its primitives. -* The API is built using [FastAPI](https://fastapi.tiangolo.com/) and follows +* The API is built using [FastAPI](https://fastapi.tiangolo.com/) and follows [OpenAI's API scheme](https://platform.openai.com/docs/api-reference). * The RAG pipeline is based on [LlamaIndex](https://www.llamaindex.ai/). -The design of PrivateGPT allows to easily extend and adapt both the API and the +The design of PrivateGPT allows to easily extend and adapt both the API and the RAG implementation. Some key architectural decisions are: * Dependency Injection, decoupling the different componentes and layers. -* Usage of LlamaIndex abstractions such as `LLM`, `BaseEmbedding` or `VectorStore`, - making it immediate to change the actual implementations of those abstractions. -* Simplicity, adding as few layers and new abstractions as possible. -* Ready to use, providing a full implementation of the API and RAG - pipeline. +* Usage of LlamaIndex abstractions such as `LLM`, `BaseEmbedding` or `VectorStore`, + making it immediate to change the actual implementations of those abstractions. +* Simplicity, adding as few layers and new abstractions as possible. +* Ready to use, providing a full implementation of the API and RAG + pipeline. Main building blocks: * APIs are defined in `private_gpt:server:`. Each package contains an `_router.py` (FastAPI layer) and an `_service.py` (the - service implementation). Each *Service* uses LlamaIndex base abstractions instead + service implementation). Each *Service* uses LlamaIndex base abstractions instead of specific implementations, decoupling the actual implementation from its usage. -* Components are placed in - `private_gpt:components:`. Each *Component* is in charge of providing - actual implementations to the base abstractions used in the Services - for example - `LLMComponent` is in charge of providing an actual implementation of an `LLM` +* Components are placed in + `private_gpt:components:`. Each *Component* is in charge of providing + actual implementations to the base abstractions used in the Services - for example + `LLMComponent` is in charge of providing an actual implementation of an `LLM` (for example `LlamaCPP` or `OpenAI`). ## 💡 Contributing @@ -105,8 +105,8 @@ typing checks, just run `make check` before committing to make sure your code is Remember to test your code! You'll find a tests folder with helpers, and you can run tests using `make test` command. -Interested in contributing to PrivateGPT? We have the following challenges ahead of us in case -you want to give a hand: +Interested in contributing to PrivateGPT? We have the following challenges ahead of us in case +you want to give a hand: ### Improvements - Better RAG pipeline implementation (improvements to both indexing and querying stages) @@ -120,7 +120,7 @@ you want to give a hand: ### New features - Implement concurrency lock to avoid errors when there are several calls to the local LlamaCPP model -- API key-based request control to the API +- API key-based request control to the API - CORS support - Support for Sagemaker - Support Function calling @@ -134,11 +134,11 @@ you want to give a hand: - Dockerize the application for platforms outside linux (Docker Desktop for Mac and Windows) - Document how to deploy to AWS, GCP and Azure. -## +## -## 💬 Community +## 💬 Community Join the conversation around PrivateGPT on our: -- [Twitter (aka X)](https://twitter.com/ivanmartit) +- [Twitter (aka X)](https://twitter.com/PrivateGPT_AI) - [Discord](https://discord.gg/bK6mRVpErU) ## 📖 Citation