Комментарии:
Dave, you're very entertaining and a pleasure to listen to. Thanks for the very informative content!
ОтветитьThis is so easy I did it in ROBLOX. Use a a custom lua context matrix network for optimization and context awareness in a local client. Then it uses a interference model for zero-shot reasoning the prompt to a variety of 10 AI APis and wikipedia. Fun stuff! But its a novel idea, that has been done a lot lately.
ОтветитьHey David, the code works perfectly. I'm planning to build a chatbot with RAG. In addition to the past conversations, I intend to add more documents related to the domain knowledge of my chatbot's use case, based on which the answers should be generated. Could you please help me with how to do that?
ОтветитьLove finding a Pioneer early.
ОтветитьBeautiful video, pure amazing content! (My first watching you.)
ОтветитьYou are a bit too technical for me, but maybe you could direct me to what I’m looking for. I just want something like chatgpt that can access or keep notes, so that it remembers our conversation OR i can write notes out that it accesses as truth.
Mainly for fantasy writing purposes.
Chatgpt loses its focus after about 30 questions it won’t remember things i asked it to remember at the start of the conversation.
prepare somehow first before the video.
ОтветитьSo I am primarily a web engineer and may main stack is web/node and dipping into AI. My main question is that the local dev seems to be in python and that makes sense, but for production is that also the best vs using node?
ОтветитьThe real question is.. when should we use vectors vs keyword vs other method to retrieve Information? I'm new to the channel, thanks for the work you put into the videos
Ответитьbro you use Notepad+ with light theme? Come one, just gouge my eyes already haha
ОтветитьI would have used GPT-4 to help write the code. Also, I was doing this while watching your video.
ОтветитьExtremely interesting architecture. Gonna pitch something to a big database company. Would it be possible to chat with you about vector DBs and semantics, etc.? I don't believe in free work, so I can think of something for your time once we secure funding.
Ответитьyou are good
ОтветитьCan you upload it to vercel ? please teach us
ОтветитьGreat video, but I had to turn it off once I saw that one of your spokes was bent. 😜
Ответитьai is definitely going to replace those idiots pretending to be a developers pretty soon.
ОтветитьI was following along until I realized that the Open Ai API isn't free 😆
ОтветитьThank you for this tutorial, but I'm running into some issues, when I try to change the convo length it doesnt seem to reflect the change, and the bot still remembers all the messages in the current session. But when I ask it things, and then quit and then ask to see if it remembers it doesn't remember what I've asked. Is there a way to fix this? I just used your code from the github.
ОтветитьFirst of all. Thanks for this amazing content. I'm of limited financial means, but I'm going to find a way to support your work however i can.
Im in the process of impending a similar philosophy. But my AGI(ACI) keeps randomly crashing from attempting to process or assimulate things with too many tokens at once. I then have to restart it, but after reinitialization it has no memory of anything it did before the crash. This gets very frustrating. Is pinecone integration going to be helpful with this?
I went into this looking for the solution to a different problem but your video was excellent to watch. I'm looking for a solution to the token limitation problem. I have large json documents of metadata that I want to use with the OpenAi api to set seed parameters for content generation. The json documents themselves can be upwards of 10k characters. The project is functionally like a reimagining of the Semantic Kernel book authoring demo where a user can set parameters to define characters, settings, locations, story structures, pacing, tone etc. Other than waiting for apis to have larger token limits or shrinking my json document, are there any ways you can think of to reference large json documents as part of semantic functions?
I'd love to say "here is your seed data (blob of json) Perform X task with these input parameters folded into your content". Then later be able to continue referencing and updating the json as I get into a create/review/update feedback loop.
I might just have to selectively use fields in my json for now until access to a LLM with a token limit in the tens of thousands is available, and has more than 25 api calls per 3 hours :)
Looking for a more simple implementation or similar?
Ответить👀"you're all watching this on 2x speed anyway" i am seen
ОтветитьTalking to herself, That's So Raven
Ответитьwhat if you use every conversation and just use that to train a fluid neural network that is never frozen acting only as smaller parameter vector space memory for the oracle neural network?
ОтветитьHey man, so I followed all of your instructions to a T. However for some reason the bot is still stupid, it doesn’t even remember the previous prompt and response. I really need help to figure out how to get it to remember context and store the information I give it. To give you context I am trying to build an AI band Manager that will help us stay organized and consistent with our social media/ develop a marketing plan. This requires it knowing everything about or band. Can you make a video about how to make it not stupid?
ОтветитьAnybody agree or disagree, in this digital Era ads are must to survive one who makes such useful content. There is no problem to viewers like me to have ads in such contents but it should not kept in middle of the video. Please keep the ads at starting or end, you'll be supported. Thank you.❤
ОтветитьIs this code available anywhere to kickstart a mini at home project? I poked around in your GitHub and didn’t see it.
ОтветитьHow did it know what pinecone vector databases are if they didn’t exist before it’s cutout date to internet data.
Ответитьi liked the video and was hoping that you would share the code at the end of the video, I am new to coding and was searching for a way to extend the memory on chatgpt. I would greatly appreciate it . thank you
ОтветитьI can't unsee the bent node now, thanks! haha
Love your work, btw!
So many digressions ... Couldn't keep up after 6-7 mins
Ответитьwhat kind of hardware are you using ?
ОтветитьI'm always watching at normal speed. Not native speaker.
ОтветитьAwesome content! But uh ..Maybe you could use ai to help edit the fluff and rambling out of your videos.
ОтветитьI might join patreon if you put notepad++ in dark mode, my eyeballs are on fire
ОтветитьBravo. I knew about pinecone and semantic search but the missing piece for me was your implementation of the nexus directory. I hadn't considered a way to get that meta information loaded up for the memory.
ОтветитьGreat Scott! 😮
Ответитьhey dave im actually just a few weeks old into programming (python), and i kept hitting snag after snag after snag, trying to port Raven into Discord as a bot, so that i can chat to him there instead. (chatting with him on the windows command line got old real quick.)
got to a point where it all seems to KIIIINDA work, but raven will then stop replying and just repeat the same block of irrelevant text no matter what new questions i asked him.
can you do a quick tiny little update so that we can use raven on discord as a bot please? thank you!
👁🔺
ОтветитьWe will look back on this in just another month and be like meh
ОтветитьI'm trying to use pinecone for my own project, I've noticed either the semantic search isn't very good or I don't know how to use it properly. I even tried passing in a part of the indexed files word for word and it didn't give me the appropriate document back.
ОтветитьI love this idea and would love to see it implemented with GPT4ALL but correct me if I am wrong, it seems to me that there is no feedback loop in consequence there is no learning or improving from it's own interactions.
ОтветитьJust had a thought, isn't the OpenAI Embedding API just how we might let the 2AI's talk directly to each other, and not in a NLP? We are building it into all the API's for them...
ОтветитьLike humans, chatbots chat too much: the underlying cause of poverty in the modern world is global Capitalism.
ОтветитьHow will speech inflection AI interpret a "while true" command, lol? AI can greatly reduced mortality rates during egresses and ingresses for refugees....RIP Aylan ....another OCDer here. Subbed.
ОтветитьI have been fighting with chatgpt to make something like this for a while now ^^' Thanks for the vid, it's got my chat bot of the ground
Ответить