Відео

Hey great questions, I'm also considering working on such. Did you figure out answers to your questions? they will help me better understand the usability of this as well

I did meet her and was able to talk to her personally! It was definitely great. Joining her session presented with Amy Hodler will make you realize you don't want to miss another one! 😊

Thanks for sharing your experience! As you referring to standard RAG (purely vector-based) or graph-based? Purely vector-based RAG is not great, while graph-based RAG could return more reliable results. But I also have to be honest that prototypes are generally cute and are very far from production-ready. That's why we need a lot of testing/evaluations, and I'm currently gearing towards making videos containing production-oriented testing :) Here's a video that I did some testing: ua-cam.com/video/mHREErgLmi0/v-deo.html

I'm surprised and also thrilled that finally someone takes my not-so-funny joke in the video seriously! 😂 Love you concise and scientific explanation of the multi-dimensional space, which makes me dream more about having that superpower. 😉 Thanks for the encouragement once again. I'm learning a lot from you guys too and have been enjoying the journey with you all!

@@lckgllm Oh good. When you make it to the fourth dimension, please give a holler! :) It would be fun to see you in two places at the same time. Three even! XD. In the meantime, please keep us posted as to your coding progress. I find your videos really helpful. Thanks!

Totally agree with you :) I have since upgraded to epidemic sounds for music and be more mindful that the music volume should not distract the viewer when I'm speaking. I'm trying to learn and become better after every video, so really appreciate seeing feedback like this for improvement!

Thanks for the encouragement! 😊

Hi Kris! Thanks for the encouragement :) I didn't stop posting. Instead, I'm posting videos on another channel I work for (e.g. ua-cam.com/users/shortsoJVRWGfqfjQ) I will try hard to post more videos about knowledge graphs and LLMs.

@@lckgllm I didn't know about the other channels. Thanks for letting me know!

Love your idea! It’s totally possible to create KG based on multiple csv files, but can you say more about what “content” means in your case?

@@lckgllm What I mean by content is csv data here

Same problem for me. Trying to implement text_for_kg.

Hello! Sorry for the late reply, been busy with work. I just realized that text_for_kg() somehow was deleted from the notebook, but it should be the same thing as diffbot_nlp.nlp_request(). I just updated the notebook in the girhub repo. Let me know if it doesn't work. I'll do my best to fix it. Thanks for point this issue out! @souzajvp

Yes I have previously used spacy-llm in my last video:ua-cam.com/video/mVNMrgexxoM/v-deo.html However, from the results generated by spacy-llm in my GitHub, you can see that there are still errors in the output, and I need to further pass the results to ChatGPT-4 for refining: github.com/leannchen86/openai-knowledge-graph-streamlit-app/blob/main/openaiKG.ipynb I hope future LLMs (regardless of closed source and open source) will enable us to see the confidence score for the output as I experienced with Diffbot's APIs.

thank you@@lckgllm ! I will have a look @ the video and the notebook. Might come back for discussion again. have a good one!

Yeah I think so! That's a great idea for a new video :)

@@lckgllm yes. I would be glad to collaborate on such project.

Thanks for the feedback! I have previously used spacy-llm in my last video:ua-cam.com/video/mVNMrgexxoM/v-deo.html However, from the results generated by spacy-llm in my GitHub, you can see that there are still errors in the output even if examples are included in the prompts, and I needed to further the pass the results onto ChatGPT-4 for refinement: github.com/leannchen86/openai-knowledge-graph-streamlit-app/blob/main/openaiKG.ipynb I hope future LLMs (regardless of closed source and open source) will enable us to see the confidence score for the output as I experienced with Diffbot's APIs.

@@lckgllm If you'd like to have confidence score using llms, a simple hack is, add that into the prompt, so llm returns the result with scores. :)

Just checked DGraph out! Didn't know about that before, thanks for sharing the info :)

Thanks! 🥳

What face filters? I literally talked in front of my MacBook Pro 14. I did have makeup on which I admit.

@@lckgllm you're fine do not worry about it. however, the audio sounds like it has a low bitrate.

Definitely going get a mic for better voice quality. Thanks for the feedback, folks!@@Armoredcody

Definitely a great question! I didn't include the process in this video and plan to make another video about this, but let me show you the details via email :)

@lm Would be highly appreciated! 🙏 Didn't get it yet though...

​@@lckgllm Hi Leann, I had the same question. Isn't this just an implementation of streamlit-agraph? Is there any reason why you left this out of the GitHub repo you shared? It would be incredibly helpful/instructive to see the implementation.

Good question, although I'd defend that the answer at 6:26 is good enough for my use case😂, as my purpose was converting unstructured text data into structured knowledge graphs, which served as the ground truth for LLM to find out the answer. 6:26 exactly showed the context from my knowledge graph. I think what you're asking "whether the graph DB could essentially act as an index for the original content" is a different use case, where the documents themselves are classified as nodes and edges would be appended to the nodes based on their semantic similarities. I'd probably make another video particularly for this use case, which is different from what you saw in this current video.

​@@lckgllm not the entire document, but rather the section of it that corresponds to the creation of that node/edge. E.g. *Graph response:* [Amy] interested_in [science history] *Source text:* "Amy has a love for science history and a fascination for complexity studies" If it was possible to store the source text as an attribute of each relationship and return that rather than the edge names then you'd probably get a higher quality answer.

Ohh!! I like this idea, yes it would be more concrete and reliable. Thanks for sharing! Let me try to improve this feature and may make a video about it ;) Really appreciate your feedback, thanks of much ❤@@AndrewNeeson-vp7ti

Hi! Thanks for pointing that out. I just added the zeroshot.cfg to github.com/leannchen86/openai-knowledge-graph-streamlit-app You can also find the document here: spacy.io/usage/large-language-models#zero-shot-prompts

I think I didn't get my point across clearly and sorry about that. In terms of constructing a knowledge graph, from my experience, currently Diffbot's Natural Language API has the best performance regarding Named Entity Recognition (NER) and Relationship Extraction (RE) compared to GPT-4 (so far the best LLM) or spaCy-llm as I tried them both. Frankly speaking, large language models are not inherently optimized for tasks as entity/relationship extractions and we should think again whether LLMs are the best option for every single task.

@@lckgllm Everything's a nail if you only wield an LLM =D

🤣@@SlykeThePhoxenix

hey daniel, what are the better performing and cheaper alternatives for NER?

Good question! I want to know too :) @danielneu9136

@@lckgllm Use small open source encoder models for NER e.g fine-tuned versions of ALBERT. Simply import the right model from the huggingface transformers library and let it label your dataset. They often perform better than LLMs on the tasks that they are trained for and most of them even work with colab free tier :)

It's true that it's expensive, and they're currently more focused on enterprise clients. The Natural Language API I use is primarily for constructing a knowledge graph in this project, as the knowledge graph serves as the foundation for my Graph RAG AI assistant (where GPT-4 is the LLM used to query the knowledge graph). I tried Diffbot's API because GPT-4 is not yet perfect at extracting entities and relationships, which are crucial for building a knowledge graph, see 5:37. GPT-4's cost can escalate significantly with large document sizes too. While I don't mind paying for accurate results, expensive and erroneous outcomes are not justifiable expenses for me. Diffbot also shows you how the API extract and evaluation information at 2:55. Do you need to build a knowledge graph for your LLM-based app? If not, you might not really need Diffbot's API as I did.

Good question @shingyanyuen3420 ! Sorry for not making it clear in the video, will improve my explanation next time. The typical RAG applications chunk documents into smaller parts and convert them into embeddings, which are lists of numeric values. LLM then retrieves information based on similarity to the semantic question. However, the information retrieval process can become challenging as document sizes increase, potentially causing the model to lose the overall context.. This is where knowledge graphs can be useful. Knowledge graphs explicitly define the relationships between entities, offering a more straightforward path for the LLM to find the answer while staying context-aware - improving accuracy for the retrieval process. Hopefully this article is helpful: ai.plainenglish.io/knowledge-graphs-achieve-superior-reasoning-versus-vector-search-for-retrieval-augmentation-ec0b37b12c49