Document summarization and question-answering on document -LLM + LangChain
It is known that large language model (LLM) based chat can answer any query with satisfied accuracy. But when ask questions about the fact, in particular the fact is the latest reported and is not covered in the training data...
Human-like communication with LLM chat agent
Imagine natural talking with your chatGPT rather than mannually input prompt and read the text response. You speak out the information requirement, and the agent speaking out the response. The solution is to integrate multiple AI modules, frontend and backend...
Streamlit: how to auto play audio, video including video size
I am currently working on the talking avatar project and use streamlit to build the demo. Streamlit audio and video function cannot support autoplay and change video window size when playing. Search and find a solution foor audio, i.e. encoding...
Draw.io, a beautiful tool to draw graph and flow
If you have difficulty to drawing a business roadmap flow, product design flow, ......., using MS Office, you can try drawio, a free drawing tool. It is easier to use. You can visit https://app.diagrams.net to use the tool and save...
YouTube channel is online
Due to the the video costing large storage, I opened a Youtube channel, Aitechcom to share video content. The blog is a mainly host site of text content. Welcome to subscrible my Youtube channel.
Llama.cpp,let running LLM in low vRAM gpu smoooth
It is impossible to running large language model such as LLama having 7B parameters in a consumer GPU, having 10GB vRAM or even lower. Llama.cpp rewrites inferfence using c/c++, and make LLM inference available in consumer low vRAM, and even in...
Captcha recognition
A CAPTCHA is a type of challenge-response test used in coomputing to determine whether the user is human in order to deter bot attacks and spam. In the captcha test in the website, a captcha image is display to the user, who recognizes...
How to setup huggingface environment to save models and data in your specified directory
Normally, when using huggingface to load pretrained model and load data from huggingface, it will check if these models and dataset are available in its cached location. By default, the location is#for mac & ubuntu, the root location of huggingface...
Singapore heritage trail: Emerald Hill at orchard
Emerald Hill, one of Singapore heritage trails, enjoy peace and rest in the crowded orchard road.https://youtube.com/shorts/HKMEB2-ycqE?si=ikI1EpGib0KpdBuA
2024 first day: Bukit Timah hill
Time flies so fast. It is 2024 already. Climbing bukit timah hill is a traditional celebration event of new year together with friends. The 2024 first day is great for hiking, a little cloud, not hot as usual. Bukit Timah...
Family of otter, wandering neighbourhoods
It happened on Monday, in neighbourhood of hdb building. The family of 4 otters, I think, should come from Alexandra canal, about 500 meters away. Arriving hear they could cross several car roads. It is dangerous to them. Bless them...
/usr/lib/x86_64-linux-gnu/libstdc++.so.6: version GLIBCXX_3.4.29 not found
In stable diffusion, when using scipy module. Sometime an error happens: /usr/lib/x86_64-linux-gnu/libstdc++.so.6: version GLIBCXX_3.4.29 not found.Googling cannot find a solution, install linux cannot fix. The error is caused by scipy version is too high (latest version). After uninstall scipy and...
