chatgpt-retrieval-plugin
chatgpt-retrieval-plugin copied to clipboard
openai
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
Hello there, Great job you are doing and excited to see more! I am thinking of providing a plugin, but I would like to consume it by querying ChatGPT API...
Even though discussed #32, still in trouble when I am upsertng with no `source` parameters.
added default value instead of conditional for the Collection Name
After building a bunch of different llm apps I found that most of them don't require much more than hnswlib + sqlite for retrieval. This combo scales up to millions...
Because the tokens of the subtext may be different from the original text, when truncating tokens, keep different tokens at the end to avoid losing some keywords. Bug reproduction text...
Hi, I found it's a very interesting repo, it recommends some vector search services, I wonder why not use some vector search libraries instead of services, personal scene retrieval candidate...
While testing/running local plug-ins - I can as a developer fully automate the tests and debug but cannot do the same when the plugin interacts with OpenAI on the plug-in...
Adds support for Elasticsearch datastores to use with the ChatGPT retrieval plug in. closes #52 Note that because of Lucene limitations, Elasticsearch does not support vectors with dimensions > 1024....
Add support for Azure Open AI embeddings. Allow Azure OpenAI deployment_id to be used in create embedding call.
Using the `with` keyword to automatically manage the resources of the open file. This removes the need for the developer to have to remember to `close` the file.
