Thanks! Glad you enjoyed it :)

Thank you :) I appreciate you commenting, and I'm glad you enjoyed it. Please go build something cool!

You're welcome, glad it helped! I try to keep the code accurate, but sometimes I think these libraries update/change really fast. I think I'll need to lock/freeze package versions in future videos so it doesn't drift.

Thank you for your comment! I'm really glad to hear it was easy to follow - well done! Hope you build some cool stuff with it :)

Really glad to hear you got it to work :) Thanks for sharing your experience with it as well - that's the whole reason I make these videos!

Thank you! Glad you enjoyed it. Thanks for the LangGraph suggestion. I hadn't noticed that feature before-tech seems to move fast in 2024 :)

Thank you! Glad you enjoyed it!

Glad to hear that! Good luck with your app.

Thank you, I'm glad you enjoyed it!

Thank you! I’m very glad to hear it was helpful for you ☺️

Glad you enjoyed it. Thanks for subscribing!

Thanks, I appreciate it!

You're welcome! And great idea for a new video :)

Thank you, I really appreciate it!

Thank you! Glad you liked it.

If you are using a local LLM, then it might depend on your computer specs. If you are using a cloud AI (e.g. AWS or OpenAI), it might be a connection bottleneck. Normally it doesn't take more than a few seconds to me for 10 pages, so it does sound like a performance issue.

You're welcome, glad you liked it!

You're welcome! I'm very happy to hear that it was useful for you :)

Thank you! 🤩

Thank you! Glad you enjoyed it :)

What changes have ben done, I cant get this to work :-(

​I haven't tested this yet but I believe everything that was from langchain import ... is now from langchain_community import or langchain_community.---.--- etc​@@niklasvilnersson24 Other than that I believe that what I used recently nothing else changed. I'm probably wrong tho

Glad it was helpful!

Glad it was helpful!

Thanks! That's a good idea too. You can probably achieve that by detecting what type of file you are working with, and then using a different parser (document loader) for that type. Langchain should have custom document loaders for all the most common file types.

Glad you enjoyed it! Thanks for the suggestion :)

You're welcome @@pixegami

Thank you!

Thank you!

Glad it was helpful!

Glad you liked it!

Thank you!

Glad to hear it was useful!

Thank you! Glad you liked :)

Glad you enjoyed it!

Thank you!

Glad it helped!

Thank you! Welcome :)

Glad it was helpful!

Glad you enjoyed it!

Yup! I think it could be useful for searching through unorganised documents too.

Glad you liked it!

Glad you liked it! Thank you. If you want to add (modify) the ChromaDB data, you should be able to do that after you've loaded up the DB: docs.trychroma.com/usage-guide#adding-data-to-a-collection

Glad you enjoyed it! I try to keep my content short and useful because I know everyone is busy these days :)

@@pixegamihey great work can we have an updated version with the langchain imports because its throwing all kind of errors of imports which are changed

Thank you!

Thanks for the feedback. I generally use OpenAI because I thought it was the easiest API for people to get started with. But actually I've received similar feedback where people just want to use open source (or their own) LLM engines. Feedback received, thank you :) Luckily with somehitng like Langchain, swapping out the LLM engine (e.g. the embedding functionality) is usually just a few lines of code.

@@pixegami It's a pleasure :). Yes, everyone seems to be using OpenAI by default, because everyone is using chatGPT. But there are lots of good reasons why one might not wish to get tied to open AI, anthropic, or any other cloud-based provider besides the mounting costs if one is developing applications using LLM. E.g. data privacy/integrity, simplicity, reproducibility (e.g. chatGPT is always changing and that is out of your control), in addition a general suspicion of non-open-source frameworks whose primary focus is often (usually?) on wealth extraction, not solution provision. There is not enough good material out there on how to create a basic RAG with vector storage using a local LLM, something that is very practical with smaller models e.g. mistral, dolphincoder, Mixtral 8x7b etc., at least for putting together an MVP. Re: avoiding openAI: I've managed to use embed_model = OllamaEmbeddings(model="nomic-embed-text"). I still get occasional 'openAI' related errors, but gather that Ollama has support for mimicking openAI now, including a 'fake' openAI key, so am looking into that as a fix. ollama.com/blog/windows-preview I also gather that with llama-cpp, one can specify model temperature and other configuration options, whereas with Ollama, one is stuck with the configuration used in the modelfile when the Ollama-compatible model is made (if that is the correct terminology). So I may have to investigate that. I'm currently using llama-index because I am focused on RAG and don't need the flexibility of langchain. Good tutorial in the llama-index docs: docs.llamaindex.ai/en/stable/examples/usecases/10k_sub_question/ I'm also a bit sceptical that langchain isn't another attempt to 'lock you in' to an ecosystem that can then be monetised e.g. minimaxir.com/2023/07/langchain-problem/. I am still learning, so don't have a real opinion yet. Very exciting stuff! Kind regards.

Wow, so generous :) Thank you. Glad you enjoyed it.

Thank you! I'm glad to hear that.

Glad you enjoyed it! I think if you want to display images, or link/share resources via the chunk, you can just embed it at chunk creation time into the document meta-data. Upload your resource (e.g. image) to something like Amazon S3, then put a download link into the meta-data for example.

Yup! Great question. I'll have to work on that, but in the meantime here's a page with all the LLM supported integrations: python.langchain.com/docs/integrations/llms/

Check out this more advanced RAG tutorial: kzfaq.info/get/bejne/aLp6q9OqtJnJmWg.html And how to deploy it to the cloud (AWS): kzfaq.info/get/bejne/osp2grFz1JingmQ.html

Yes! Check out this video on how to use different models other than OpenAI: kzfaq.info/get/bejne/ft5_m8iix5y1nYU.html And here is the official documentation on how to use/implement different LLMs (including your own open source one) python.langchain.com/docs/modules/model_io/llms/

Thanks! I haven't looked at how to use the Langchain memory feature yet so I'll have to work on that first :)

@@pixegami ohk i i have implemented memory and other features also also as well as worked with windows also after some monstor errors,, thank once again for the clear working code (used in production) hope to see more in future

I use iTerm2 for videos because it looks and feels familiar for my viewers. When I work on my own, I use warp (my terminal set up and theme explained here: kzfaq.info/get/bejne/q82noKuQ3eDPc3U.html) And if you're using Ubuntu, I have a terminal setup video for that too: kzfaq.info/get/bejne/i9yJaMR3rbTTdas.html

Glad it was helpful! Running local LLM apps is something I get asked quite a lot about and so I do actually plan to do a video about it quite soon.

@@pixegami Yes please!

You can create custom apps for Businesses using their own documents = huge Business opportunity If it really works.

Yeah that's a really good point. What I really needed was a data-source that was easy to understand, but would not appear in the base knowledge of any LLM (I've learnt that now for my future videos).

Thanks :) It seems to be a popular topic so I've added to my list for my upcoming content.

If made video on above request kindly give link in description it gonna be a good for all users

Instead of md extension you can simply use txt or pdf extension thats it just replace the file extension

Yes, pls share how to work with pdfs directly instead of .mds . Thanks !

Yup, you should be able to override the evaluator (or extend your own) to use whichever embedding system you want: python.langchain.com/docs/guides/evaluation/comparison/custom But at the end of the day, if you can already get the embedding, then evaluation is usually just a cosine similarity distance between the two, so it's not too complex if you need to calculate it yourself.

Yes, you can basically load any type of text data if you use the appropriate document loader: python.langchain.com/docs/modules/data_connection/document_loaders/ Text files are an easy example, but there's examples of Wikipedia loaders in there too (python.langchain.com/docs/integrations/document_loaders/). If you don't find what you are looking for, you can implement your own Document loader, and have it get data from anywhere you want.

@@pixegami Exactly the question and answer I was looking for, thanks

I use Monokai Pro :)

The VSCode theme is called Monokai Pro :)

Thank you, welcome! To calculate pricing, it's based on which AI model you use. In this video, we use OpenAI, so check the pricing here: openai.com/pricing 1 Token ~= 1 Word. So to embed a document with 10,000 words (tokens) with "text-embedding-3-large" ($0.13 per 1M token), it's about $0.0013. Then apply the same calculation to the prompt/response for "gpt-4" or whichever model you use for the chat.

That's a tactical question that will vary from doc to doc. It's a great question and a great use-case though for creative problem solving-thanks for the suggestion and video idea.

If you want a simple, Python based one, try Streamlit (streamlit.io/). I also have a video about it here: kzfaq.info/get/bejne/epZ0Z7OSl5jNd2Q.html

There's currently a lot of different research and tools on how to evaluate the output - I don't think anyone's figured out the standard yet. But stuff like this is what you'd probably want to look at: cloud.google.com/vertex-ai/generative-ai/docs/models/evaluate-models

Haha that's a topic for another video. But yeah, if the data is not good, then I think that should be your first focus. This RAG technique builds on the assumption that your data is good-and it just adds value on top of that.

The NLTK library? I don't think I had to use it here in the project, a lot of the other libraries might give you all the functionality at a higher abstraction already.

Thanks! I'm working on a video to explain techniques like that. But in a nutshell, you'll need to attach an ID to each document you add to the DB (derived deterministically from your page meta-data) and use that to update entries that change (or get added): docs.trychroma.com/usage-guide#updating-data-in-a-collection

Thank you! I normally just store the OpenAI key in the environment variable `OPENAI_API_KEY`. See here for storage and safety tips: help.openai.com/en/articles/5112595-best-practices-for-api-key-safety

Ah, if you change the source document, you actually have to generate a new embedding and add it to the RAG database (the Prisma DB here). So you would have to figure out which piece of document changes, then create a new entry for that into the database. I don't have a code example right now, but it's definitely possible.

Product recommendations are a good idea :) Thanks for the suggestion, I'll add it to my list.