Your videos have been awesome, I have learned so much about the current libraries in the artificial intelligence space and your opinions have given me lots of context as I learn and work on my own libraries. Thanks and keep up the good work!
AI-agent search is genuinely being revolutionized by knowledge graphs! The advancements in technology are astounding. There are more tools worth looking at if you're interested in investigating more intelligent AI solutions. #TechInnovation #KnowledgeGraph #AI
I think it would be great if we/community could implement the ability to upload PDF documents for chunking and adding to the knowledge graph. I have not had any time to thinker on adding features but I've been playing with the system prompt and graph structure.
re you planning to use Neo4j exclusively for your project, or do you still require another database for semantic search? I asked ChatGPT, and it seems that while Neo4j can handle semantic search, it may not be optimized for quick searches if the database becomes too large.
Thank you! In short, Microsoft's graph-rag is a bit more sophisticated. After it constructs knowledge graphs, it also does some community detection stuff. There's more to it than that, I don't recall all the details of the paper.
very good ! ( but ... Think Should be a tool ) ( observe should be the return tool call ) ( action : should be the selected tool or action ) ( think : should be a tool to self query for a plan or methodology or how to porceed to the next step of a plan ? ) .... This way we can create Any methodology or chain of thoughts : if we make the components Tools themselfs .. such that : create a plan ( should be a tool ( which is a prompt , to query itself with a task , so given a task as input it will return plan ) < the prompt in the chain manages this ( tool ) .... Refine Code ( this can also be a tool : As it will query itself again, with the code for refinement ( the only chage is the prompt ... Tool or chain , or Graph this will always be the question ) ... So we can have a refiner prompt : the rifiner prompt could have a set of feirce requirements to folow and use for correcting code : or indsutrialising code etc :; So when we design processes etc for our agent we can also have template plans in the planner ! < the user would like to repair some code : so the planner would offer the tool choices and even disribute a boilerplate , from a set of boiler plates : ie a code planner could have many basic template to begin a project : Supplied to the model as a list of docstrings to select a template it would call the tool to return the template from file or disk storage : ( ie tools have acess to the required system and files and do not go outp=of bounds ) ( open code execution and open syystem command executions should always be human intervention as it can destruct your system : Hence Tools istead : they have boundrys : A planner could also have acces to tool collections , which can be loaded to the agent which will perform the task : ie pass a toolbox to the model ! Hence your central controller bot will access all these tools ! given a menu of tasks , which return tool collections and plans and Start nodes : allowing the model to pass a custom state to a chain and retun its output : ie create an app which does : it would ask its general planner bot : who would tell it the correct planner to begin : then that palnner would give the agent the tools and requirements and the start node ! alowing for the agent to execute the correct Graph ( tool:) with a state and expectation ! I built this process the same way as you : But after i realised the whole above discussion : and then i realized even higher perspective : that our front end should be the same as dialog flow : as this add the personality layer ( it may not be intelligent but its the constrainment we need on top) we are currently working at a very low level and should realize that we have many layers on top of this : not a UI ! between the react process (or thought process and selected methodology for the task : as the react is very good for long and indepth tasks with a graph based structiure ) but not good for general chat ! hemmce we need the front end on top of this layer , a very simple , keyword and detect/Response method : a dialog manager : as eve the rag should be plugged in at this higher level : as it is not reuired unless its for indepth tasks : as basic chat history can keep your model personalised and up to date : the rag is a short /long term memory: whihc after optimization can be finetuned into the main llm : but it still does form a part of the reseach and content process when required ( it should be a tool ( only used when required ) ! ..as a State is enough to use to perform a task and chunking and embedding for simularity should oyu be for indepth querys ! not for dowloading and sumarizing !
Thank you for the comprehensive explanations! Your videos are worth watching. I was looking if you may have released a video regarding complex handling of state when using MemorySaver in conjunction with checkpointer that is giving me some trouble. by the way I have implemented human-in-the-loop as well, and that is when I started having an issue with state retrieval after stopping to get human feedback. Any suggestions will be much appreciated! Thanks again!
Not everything out here is AI. I use video editors to improve sound quality and also for transitions (where I have made cuts and edits). It is probably a transition you're referring to as an artefact.
Your videos have been awesome, I have learned so much about the current libraries in the artificial intelligence space and your opinions have given me lots of context as I learn and work on my own libraries.
Thanks and keep up the good work!
how you don't have more followers than any ai guru on youtube is beyond me
I'm here
I'm here there and everywhere
Thank you as always for sharing. Continue the good work you're doing.
Thank you for the support!
This is becoming my favorite AI channel. Great content!
Hey don't think he named its after you bro, it's me
@@jarad4621 Perhaps he is taking the best parts of all Jarads and making The next Level of AGI - AJI - Artificial Jared Intelligence
I'm loving this community of Jared's/Jarad coming out to support the development of Jar3d.
You named it after me! Thanks man, it's even pronounces the same ❤
Good job mate. Keep it up. I need to finf some time to go through your tutorials. In the meanwhile, I wish you all the success.
AI-agent search is genuinely being revolutionized by knowledge graphs! The advancements in technology are astounding. There are more tools worth looking at if you're interested in investigating more intelligent AI solutions. #TechInnovation #KnowledgeGraph #AI
You rock! Thanks for sharing the insights.
Thank you!
Fantastic work
I think it would be great if we/community could implement the ability to upload PDF documents for chunking and adding to the knowledge graph. I have not had any time to thinker on adding features but I've been playing with the system prompt and graph structure.
re you planning to use Neo4j exclusively for your project, or do you still require another database for semantic search? I asked ChatGPT, and it seems that while Neo4j can handle semantic search, it may not be optimized for quick searches if the database becomes too large.
What is your thoughts on integrating GraphRag or HybridRag?
Love your videos. Are you a professor?
Thanks, no not a professor.
thanks! i hope this works in gpt, groq and ollama! :D thanks!
Looking forward to trying this! Great work! My one question is, how is this similar or different from (Microsofts) GraphRag?
Thank you! In short, Microsoft's graph-rag is a bit more sophisticated. After it constructs knowledge graphs, it also does some community detection stuff. There's more to it than that, I don't recall all the details of the paper.
very good ! ( but ... Think Should be a tool ) ( observe should be the return tool call ) ( action : should be the selected tool or action ) ( think : should be a tool to self query for a plan or methodology or how to porceed to the next step of a plan ? ) ....
This way we can create Any methodology or chain of thoughts : if we make the components Tools themselfs .. such that : create a plan ( should be a tool ( which is a prompt , to query itself with a task , so given a task as input it will return plan ) < the prompt in the chain manages this ( tool ) .... Refine Code ( this can also be a tool : As it will query itself again, with the code for refinement ( the only chage is the prompt ... Tool or chain , or Graph this will always be the question ) ... So we can have a refiner prompt : the rifiner prompt could have a set of feirce requirements to folow and use for correcting code : or indsutrialising code etc :;
So when we design processes etc for our agent we can also have template plans in the planner ! < the user would like to repair some code : so the planner would offer the tool choices and even disribute a boilerplate , from a set of boiler plates : ie a code planner could have many basic template to begin a project : Supplied to the model as a list of docstrings to select a template it would call the tool to return the template from file or disk storage : ( ie tools have acess to the required system and files and do not go outp=of bounds ) ( open code execution and open syystem command executions should always be human intervention as it can destruct your system : Hence Tools istead : they have boundrys :
A planner could also have acces to tool collections , which can be loaded to the agent which will perform the task : ie pass a toolbox to the model !
Hence your central controller bot will access all these tools !
given a menu of tasks , which return tool collections and plans and Start nodes : allowing the model to pass a custom state to a chain and retun its output : ie create an app which does : it would ask its general planner bot : who would tell it the correct planner to begin : then that palnner would give the agent the tools and requirements and the start node ! alowing for the agent to execute the correct Graph ( tool:) with a state and expectation !
I built this process the same way as you : But after i realised the whole above discussion :
and then i realized even higher perspective : that our front end should be the same as dialog flow : as this add the personality layer ( it may not be intelligent but its the constrainment we need on top) we are currently working at a very low level and should realize that we have many layers on top of this : not a UI ! between the react process (or thought process and selected methodology for the task : as the react is very good for long and indepth tasks with a graph based structiure ) but not good for general chat ! hemmce we need the front end on top of this layer , a very simple , keyword and detect/Response method : a dialog manager : as eve the rag should be plugged in at this higher level : as it is not reuired unless its for indepth tasks : as basic chat history can keep your model personalised and up to date : the rag is a short /long term memory: whihc after optimization can be finetuned into the main llm : but it still does form a part of the reseach and content process when required ( it should be a tool ( only used when required ) ! ..as a State is enough to use to perform a task and chunking and embedding for simularity should oyu be for indepth querys ! not for dowloading and sumarizing !
Thank you for the comprehensive explanations! Your videos are worth watching.
I was looking if you may have released a video regarding complex handling of state when using MemorySaver in conjunction with checkpointer that is giving me some trouble. by the way I have implemented human-in-the-loop as well, and that is when I started having an issue with state retrieval after stopping to get human feedback.
Any suggestions will be much appreciated!
Thanks again!
This sounds good, I think my next iteration will be a refactor of the code and potentially something to handle context and memory more efficiently.
Cool dude. :-)
If you don’t mind, I’m wondering about the use of LayoutPDFReader with a URL. Isn’t it designed for PDF files?
It confused me initially too, it's actually a misnomer. It works for URLs too!
Is it possible for the agent to display some part of a knowledge graph to the user visually?
Potentially possible with the right UI.
You should rename this "Q**"
8:48 ?? I keep finding these artifacts in your videos. Are you AI?
Not everything out here is AI. I use video editors to improve sound quality and also for transitions (where I have made cuts and edits). It is probably a transition you're referring to as an artefact.
Why Neo4j????
Because Neo4j is amazing and LLMs love graph theory.