Видео

Thankyou so much sir, this is Gold

Sir, Can you mention if I have to install something other than the stuff in models folder?? I don't know why I am getting errors regarding langchain and stuff

Sir, Can you once checkout my code. Idk what's wrong. But I am keep getting issues with llama-cpp-python eventhough I have tried several things to fix it

Is everything used in the video free??

Can we deploy this on streamlit with the chromadb and other?

Could you make a step by step Tutorial on how you made this? I have seen your previous videos,but I want to know how you made this using Ollama.

great video i subscribed.. can you give us the modifyable interface in a zip to use it portable usb mode

thanks Leon! really great effort and work to share it! Cheers to you

Is there any possible way to lessen the response time, cause in my case it is taking around 15-20 seconds to respond, My laptop specs are: 16GB DDR5 RAM, RTX 3050 6GB VRAM GPU, i5 13th gen intel processor

This is one of the worst tutorials ever. It looks like you just took someone else's code and you just copy it

Can we consider this RAG system?

Really nice interface ! hope one day you will do a more beginner friendly tuto...i install ollama, docker but couldnt pass "docker compose up" instruction without the error " no config file provide" 😅.. i will come back in few weeks, thanks anyway

what about the code in your previous video will it work fine now cause i am follwing it and getting alot of errors also the code in that video is not the same as in the repo (that video is 8 months older)

thanks dude

Did you manage to implement a responsive voice chat mode? I'm currently using Open WebUI for about everything else and LocalAI is also pretty good. But I haven't really found a good working voice assistent yet. The projects that exist only support English and usually can not handle interruptions properly. Though I haven't checked if that has changed in the past few weeks. ;-) Finally there is also this memory issue. There was MemGPT quite a while ago and there are apps here and there that can write summarizations to a database. But I'm not aware of something that actually saves notes and also retrieves them back in context in a smart way. On the other hand, even ChatGPT is not very good at taking notes.

That was your video from a year ago that introduced me to the fascinating possibilities of what you can do with today's LLMs and countless tools. Since then, I have created many gadgets to enhance my everyday work. Thank you so much.

Get the Code here: github.com/Leon-Sander/Local-Multimodal-AI-Chat Let me know if you enjoy the Chat App 🔥 If you want to give some support: buymeacoffee.com/leonsanderai Business/Consultation Contact: leonsander.consulting@gmail.com

Thanks brother you saved my hackathon. Lots of love from india

sometbody know about this error error I am getting in audio handling ->> LibsndfileError: Error opening <_io.BytesIO object at 0x0000021FDE18F6F0>: Format not recognised.

Is it free? And the data we stored is publish only local or not?

one of the best video on youtube man this is god work you are amazing god bless you

Getting this error can you help ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (llama_cpp_python)

Thank you, this app is very cool.

I don't have a powerful machine, just a 8GB RAM and intel core i5. Will it work properly or not ?

hey, do you think these models can run smoothly without gpu on intel core i5??

I am getting this error. can someone help me ? 2024-08-20 03:39:18.711 Uncaught app exception Traceback (most recent call last): File "C:\Users\cadmin\AppData\Local\Programs\Python\Python312\Lib\site-packages\streamlit untime\scriptrunner\script_runner.py", line 535, in _run_scrip t exec(code, module.__dict__) File "C:\Users\cadmin\Documents\shipcom\multimodal\app.py", line 149, in <module> main() File "C:\Users\cadmin\Documents\shipcom\multimodal\app.py", line 68, in main chat_sessions = ["new_session"] + get_all_chat_history_ids() ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\cadmin\Documents\shipcom\multimodal\database_operations.py", line 96, in get_all_chat_history_ids cursor.execute(query) sqlite3.OperationalError: no such table: messages 2024-08-20 03:39:37.955 Uncaught app exception Traceback (most recent call last): File "C:\Users\cadmin\AppData\Local\Programs\Python\Python312\Lib\site-packages\streamlit untime\scriptrunner\script_runner.py", line 535, in _run_scrip t exec(code, module.__dict__) File "C:\Users\cadmin\Documents\shipcom\multimodal\app.py", line 149, in <module> main() File "C:\Users\cadmin\Documents\shipcom\multimodal\app.py", line 68, in main chat_sessions = ["new_session"] + get_all_chat_history_ids() ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\cadmin\Documents\shipcom\multimodal\database_operations.py", line 96, in get_all_chat_history_ids cursor.execute(query) sqlite3.OperationalError: no such table: messages

has anyone encountered this error sqlite3.OperationalError: no such table: messages

"Failed to build llama-cpp-python chroma-hnswlib ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (llama-cpp-python, chroma-hnswlib)" I've been getting this error. Anyone knows how to solve it?

Hey bro actually i wanted to use the above same project for a organization.should i use quantized models or a full size ones and what changes will you suggest for a multi user interface i am going to deploy this chatbot on a HPC so there is no any compatibility issue. Please suggest me necessary changes

can somebody help me with this issue:- Traceback (most recent call last): File "d:\AI_chat\local_multimodal_ai_chat\app.py", line 2, in <module> from llm_chains import load_normal_chain, load_pdf_chat_chain File "d:\AI_chat\local_multimodal_ai_chat\llm_chains.py", line 14, in <module> config = load_config() ^^^^^^^^^^^^^ File "d:\AI_chat\local_multimodal_ai_chat\utils.py", line 7, in load_config with open("config.yaml", "r") as f: ^^^^^^^^^^^^^^^^^^^^^^^^ FileNotFoundError: [Errno 2] No such file or directory: 'config.yaml'

30:20 (save chat history sessions by name) 51:00 (pypdfium is used, maybe try converting to markdown instead b4 embedding; reranking? source citation?) 59:45 (use conversational retrieval chain instead of RetrievalQA)

Do we need to use gpu or is it fine to use cpu

Sir am getting module object is not callable

Does anyone know why there are no new videos on this channel ?

Thanks for sharing, excellent tutorial. How could I deploy a project using an LLM model like this?

Thanks for the video. Great work.

INSTRUCTOR._load_sbert_model() got an unexpected keyword argument 'token'

Hello leon, Right now i am on basic chat implementation part and i am facing some errors.. Like when i am not using ctranformers def create_llm(model_path = config["model_path"]["large"], model_type = config["model_type"], model_config = config["model_config"]): llm = ctransformers(model = model_path, model_type = model_type, config = model_config) return llm then system give me- Typeerror: 'object is not callable error'. when i am using ctransformers def create_llm(model_path = config["ctransformers"]["model_path"]["large"], model_type = config["ctransformers"]["model_type"], model_config = config["ctransformers"]["model_config"]): llm = ctransformers(model = model_path, model_type = model_type, config = model_config) return llm system give me keyerror: 'ctransformers' please help me leon asap

till image handling everything was smooth .after that everything messed up..im getting lots of errors

Hi, could you help me? How do I use openAi key or instead of HuggingFace. Tell me how I can support you in this project, helping me with this interface.

great video, going to ask one thing, why not use huggingface instead? why do we download local models?

Hey Leon, just to understand, is the application designed so that we can add in our own data (Such as PDFs) and the responses from the chatbot will be based on the info in the data we initially inputted?

Hello sir, I thank you for all these efforts and the quality of your content. I cloned your project "local_multimodal_ai_chat" on your Github and I downloaded the models as you suggested in the README. I manage to run the application with streamlit and when I want to add a pdf I get this error. TypeError: "INSTRUCTOR._load_sbert_model() got an unexpected keyword argument 'token' "

Nice work

The way of doing job done is the best way, which I found here.

Thank you very much, i have a question if i want to only work on data from the pdfs folder and not from the model's pretrained history , can you please tell me how i can do it

Bro I'm got many errors while executing it like llm chains retrieval was depecrated, llm chains embeddings and many more can you please solve it for me

why is my model generating outputs slower than in the video. it is taling like 1 min to generate sometimes even longer. i got a rtx 4050 laptop gpu and a y=r7 7735hs processor and the same model runs faster on lm studio. please help me decrease the response time

superheroes = { "Batman": "Bruce Wayne", "Superman": "Clark Kent", "Iron Man": "Tony Stark", "AI_LLM Man": "Leon Sander" }

@leonsaiagency Can chat with pdf display a corresponding image of the problem being asked by the chatbot?