Hacker Remix

How do you organize and index your ChatGPT chat threads and chats?

7 points by profsummergig 1 year ago | 7 comments

My list of ChatGPT chat threads is growing. It's becoming onerous to organize and index my chat threads and chats.

One can rename a chat thread. So I'm trying the tack of keeping the chats for a single thread around a theme, and renaming the chat thread something related to the theme.

There's no way to directly bookmark a chat, but one can bookmark a chat thread. So I'm trying to create bookmark folders in my browser, with useful names, and put bookmarks to relevant chat threads in there.

Please share your methods for organizing and indexing chat threads and chats.

(It would be nice to have a plugin that can parse through all my threads and dump all my prompts and their responses into a table in SQLite or MongoDB, so that I can easily search them.)

jmstfv 1 year ago

I had a similar problem as well, so I wrote a code (read: asked chatgpt to write) that takes the chatgpt export file and turns each conversation into a separate markdown file, which can easily be grepped.

https://github.com/jmstfv/chatgpt-markdown

samstave 1 year ago

>(read: asked chatgpt to write)

I think the new verb should be "GPT'd"

"I GPT'd this little snippet to slurp my chats from chat.openai and dump them into this searchable blob.

samstave 1 year ago

I like to tell gpt to summarize a thread for me when I am done with it for the time being - so I can get a tl;dr and an eli5 and a bullet list of a thread's main points...

A meta-convo tool would be cool to watch your chats and then have a journal of "on this day you talked about these topics" and you can click for context/history/summary....

It would also be cool to in later chats be able to tell it to reference that previous thread for context.

So if you have a bunch of threads on "chemistry" tell gpt to ingest your personal corpus of chemistry for context as it relates to other trains fo thought.

Is there such an AI notebook?

---

>It would be nice to have a plugin that can parse through all my threads and dump all my prompts and their responses into a table in SQLite or MongoDB, so that I can easily search them

Matrix.org has such a plugin:

https://gitlab.com/etke.cc/tools/emm

I wonder if it could be adapted.

---

I am currently on GPT/LLM ADHD overload...

I've installed several tools fooocus, S=table Diffusion, Scenario.com too many discords, copilot in VScode...

I feel like I need a fresh full machine and install all tools in a more thoughtful manner - I feel tool-overload...

Any advice on this would be helpful. It feels like everything is so fragmented.

mendeza 1 year ago

Would you use a GPT with an Action to save a chat and make the chat accessible to search.

samstave 1 year ago

yes, locally.

THinking about it, if you're going to make this - then make it do a summarization of the chat thread at the end, then dump the summary with then a link to searching the thread - so if you look up a topic, it will first give you the summary of the thread's content.

Then, you can ask it "tell me the gist of the chats I have had, and have it give a high level summary of the topics of each thread's summary's topics...

So it would reply like:

You've talked about X, y and Z in the past week, mostly related to [topic] you seemed to grasp the most about [topicX] and had the most questions about [topicY]

which thread to revisit?

Create a new thread merging the topics together, etc so you can merge bodies of learning that you have in your chats and keep the original threads/chats.

Kind of like an "*AI Powered Version of CONNECTIONS - the old TV docu-series about how inventiones fed into eachother over decades)

mendeza 1 year ago

I really like these ideas here! Is privacy a key value proposition here? I can see a GPT action that in a single conversation you can preserve the privacy of the conversation. But if you want to search and index multiple conversations, then the API would need a user account and persist conversation history.

aine 1 year ago

emm is quite simple, so yep, you totally could adapt it - just replace matrix part with your own thing