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.
2024-03-11 14:37:32.581 | INFO | datastore.providers.redis_datastore:_query:313 - Gathering 1 query results 2024-03-11 14:37:32.581 | DEBUG | datastore.providers.redis_datastore:_query:315 - Query: string 2024-03-11 14:37:32.582 | INFO | services.date:to_unix_timestamp:23 - Invalid date format:...
`services.openai.get_embeddings` does not expose the `dimensions` kwarg of `openai.Embedding.create`
Although EMBEDDING_DIMENSION is described as a required variable in the README , it is not used, except in a few of the datastore's setup.md instructions to create their vector indexes....
I attempted to set up a server for using the chatgpt-retrieval-plugin, configuring the vector database to Chroma as per the instructions in the README.md However, I encountered a failure in...
So I was working on some research paper and I provided GPT (3.5) with a big prompt and when I tried to copy that prompt it start glitching the UI....
"...and can be used with [ChatGPT custom GPTs](https://chat.openai.com/gpts/discovery), [function calling](https://platform.openai.com/docs/guides/function-calling) with the [chat completions](https://platform.openai.com/docs/guides/text-generation) or [assistants APIs](https://platform.openai.com/docs/assistants/overview), or with the [ChatGPT plugins model (deprecated)](https://chat.openai.com/?model=gpt-4-plugins)...." it says in the Readme but...
I followed all instructions to run the plugin, when I run `retriever.get_relevant_documents("some text .. ")`, I always get this error  what is the cause and how to fix it,...
``` poetry-env) nyck33@nyck33-lenovo:~/projects/chatgpt-retrieval-plugin-nyck33-fork$ poetry run pytest -s ./tests/datastore/providers/supabase/test_supabase_datastore.py ========================================================= test session starts ========================================================== platform linux -- Python 3.10.13, pytest-7.3.1, pluggy-1.0.0 rootdir: /home/nyck33/projects/chatgpt-retrieval-plugin-nyck33-fork configfile: pyproject.toml plugins: asyncio-0.20.3, anyio-3.7.0, cov-4.1.0 asyncio: mode=auto...
`upsert` allows to specify the document ids, but `upsert-file` does not support this option.
