chatgpt-retrieval-plugin

Many comments are criticizing the usage of LLM for this use case but I do believe this will become more common in the future. For example, OpenAI's retrieval plugin leverages LLM to do PII detection [1] instead of using the traditional libraries [2]. [1] https://github.com/openai/chatgpt-retrieval-plugin/blob/main... [2] https://github.com/topics/pii-detection

There is this https://github.com/openai/chatgpt-retrieval-plugin I just use SBERT which has models I can run locally https://sbert.net/

should be yes, but even in examples from openai, they usually do splitting into chunks For example in chatgpt-retrieval-plugin[0] repo default chunk size is just 200 tokens this is anyway a limitation, no doubt, but chunking is pretty often used [0] https://github.com/openai/chatgpt-retrieval-plugin/blob/main...

Is it made using the retrieval plugin (https://github.com/openai/chatgpt-retrieval-plugin) and a custom knowledge base?

See also the ChatGPT Retrieval Plugin by OpenAI at https://github.com/openai/chatgpt-retrieval-plugin

Congrats on launching! Does Metal compete with https://github.com/openai/chatgpt-retrieval-plugin or does it provide a different value?

You can retrieve information on demand based on what the user is asking, like this: https://github.com/openai/chatgpt-retrieval-plugin

OpenAI actually thinking about this too. It’s buried in their open source repo and not clear the exact mechanism that ChatGPT knows to make use of it. But we’re already here evidently. https://github.com/openai/chatgpt-retrieval-plugin#memory-fe...

Found the answer here: https://github.com/openai/chatgpt-retrieval-plugin#retrieval... The plugin uses OpenAI's text-embedding-ada-002 embeddings model to generate embeddings of document chunks, and then stores and queries them using a vector database on the backend. As an open-source and self-hosted solution, developers can deploy their own Retrieval Plugin and register it with ChatGPT. The Retrieval Plugin supports several vector database providers, allowing developers to choose their preferred one from a list.

OpenAI already has it, it’s part of the retrieval plugin: “A notable feature of the Retrieval Plugin is its capacity to provide ChatGPT with memory. By utilizing the plugin's upsert endpoint, ChatGPT can save snippets from the conversation to the vector database for later reference (only when prompted to do so by the user). This functionality contributes to a more context-aware chat experience by allowing ChatGPT to remember and retrieve information from previous conversations.” https://github.com/openai/chatgpt-retrieval-plugin

The biggest deal about this is the ability to create your own plugins. The Retrieval Plugin is a kind of starter kit, with built-in integrations to the Pinecone vector database: https://github.com/openai/chatgpt-retrieval-plugin#pinecone

Yup, basically. Edit: see here: https://github.com/openai/chatgpt-retrieval-plugin/blob/main... I did this a while back with ARKit: https://github.com/trzy/ChatARKit/blob/17fca768ce8abd39fb27d...

This is huge, essentially adding what people have been building with LangChain Tools into the core product. The browser and file-upload/interpretation plugins are great, but I think the real game changer is retrieval over arbitrary documents/filesystem: https://github.com/openai/chatgpt-retrieval-plugin