Відео

Hi Jason, thanks for the demo, however the links you pasted for tool access, I cant access it. is this something you can share with the community

This is fantastic! All the important things to know starting from zero in a matter of moments. Well done!

I think this helped me a lot so that one day, when I meet a graph shaped problem, I'll hopefully recognize it. Probably not a video for everyone but perfect for me at this time.😊

worthless video

Amazing video❤

Thank you, this has added additional hours to my life, I wrote complete python scripts to do environmental analysis. I will check if the application has api's, as I use google alerts a lot, if it could use rss feeds as a method of automated ingestion this will have exactly what I need to setup graphs / per topic or area I have interest in and have RSS feeds populate the graph etc. etc. etc.

Thank you.

Thank you.

Thank you.

Hey love all this stuff would love to come to any bulder events if y'all are sponsering or hosting any in California?

The "Why knowledge graph?" question i feel was not answered adequately. The question is implicitly comparing KG with NOSQL/SQL so only a thoughtful and specific comparison between the two is appropriate; I'll give it a shot: The answer is "the KG is able to express ambiguity in it's syntax that isn't possible in NOSQL/SQL, or is prohibitively expensive compared to KG's which is very cheap. In cypher, we easily express Patterns, that personify ambiguity/non-completeness. This ability to speak to your Database in patterns, allows us to instruct the KG to 'Give me whatever Entity type exists at this location; node or relationship, I'm not sure what it is, but i know it matches this Pattern: <cypher pattern>' Another mental model: 'Ask a partial question to your KG, and ask it to give you a complete answer, and the complete question it answers, as an output.'. Ironically that's a very similar processes for which we use LLM's. Ambiguity in, Clarity out. KG + LLM are perfectly complementary tools. The best SQL can do as a comparison is the LIKE operator which is prohibitively expensive on a large corpus."

That is SUCH a great video! Thank you so much for it 😊

Great content ! If you could add some info about underhood on high level.. it will be much helpful.. thanks ! Also if related contents are existing/separated between UA-cam and also on gcs .. how to have 1 combined knowledge graph as per your setup.. thanks

Very cool. Looks promising!

Thanks

Beautiful.

Very informative! Thank you so much David and Alexander for the insightful discussions!

Hi, thanks for this video. I've found knowledge graph very useful when describing complex relationship among variables. However, I'm still not sure how to draw a knowledge graph to describe an interaction effect (i.e., the effect of X1 on Y depends on another variable X2). For example, "while brand commitment attenuates negative consumer responses in low-severity recalls, it augments them in high-severity recalls." this sentence depicts the interactive effect of brand commitment and severity of recalls on negative consumer responses. It would be very helpful if you provide some suggestions! Thanks always.

Thank you

great presentation. very useful

Thanks for the information, could you share the notebook ?

On-device graphrag for me is on a smartphone with 16 GB of RAM. Things I say and do that are private should stay on device. Things I say and do that I want to share should be merged into a public graph that can run collaboratively both on other personal devices and in the cloud, all open source. The small language models that can provide the interface to the graph are not good enough yet. I think the graph technology is more mature.

can you provide information regarding seed from URI for azure storage seed provider

What if I need the section and sub-section also from where in the document the answer extracted?

I tried to run the project but there's a mess with env vars and GCP configuration, it's a cool use case, but the project setup is messy

what is up with the page...? looks weird!

watched

not bery intuitive. The acid test is that I should be able to run the tool with little or no training. I can't. I had to come here and this video was too lightweight and fast-paced to be valuable... 1/10

Hello, I have a concern regarding the conversion of unstructured data into a knowledge graph. Since the process involves selecting specific words to form nodes and relationships, there seems to be a significant loss of data. How can we effectively address this issue?

😂😂😂😂😂😂😂😂

This is bullshit.. llamaindex have so much better support for knowledge graph.. with property graphs and its index.. and the full control over the graph creation..Langchain is far behind.. this app doesn't work.. and is waste of time!

Great video and great app! I have a question on how the llm is used to generate responses based on the knowledge graph. From my understanding, whether i'm using langchain or llamaindex cypher chatbot, the chatbot basically receives the prompt as well as the list of all existing nodes and relationships and from that it generates a cypher query to retrieve the relevant context from the knowledge graph to then formulate the response. But the list of all nodes and relationships will get longer for every new document being added in the graph, so since the llm is limited by its context window, isn't this approach unscalable? if so do you guys any solution to this problem? thanks in advance.

Great numbers. But this feels like a sales pitch rather than tech talk. It’s unclear to me how fanout is fixed by Neo4j? How does it impact read time since you’ll need to construct the feed by walking the graph right? Are 125-48-3 numbers of nodes per cluster or total number of nodes? If the former, how many clusters did you need? If the latter, you really only need 3 Neo4j instances in total, not even standby servers? Can you shed some light on those things? Or point me to followup video?

Automated knowledge graph construction is risky...

commands for import has changed in the latest dbms version

really good

Hi thanks for the video. What if we previously exported the output of "MATCH (n) RETURN n" into a CSV file. And now we want to upload that file into another database. Is there any way that neo4j recognizes the node types and properties automatically?

I wanted to use public app. When trying to connect I get following error: Could not use APOC procedures. Please ensure the APOC plugin is installed in Neo4j and that 'apoc.meta.data()' is allowed in Neo4j configuration

I have question, I already have ollama install in my bare-metal linux box, will docker install another instance and duplicate the models or will it fetch it from the existing bare metal installation?

it seems hard to use, at the end of the demo, the query didn't work, and author tried a select all instead, : )

Wonderful introduction to a lot of concepts. Thanks!