Technical requirements
Most of the code in this chapter can be run on CPUs. The Introduction to Streamlit and Frontend with Streamlit sections do not require GPUs. The libraries to install are as follows:
- Streamlit: For managing the frontend and backend of our app
- pandas: For handling DataFrames
- Matplotilib: For plotting graphs
- Folium: For plotting maps
- time: For monitoring runtime
- NumPy: For numerical computation
- pydeck: For map representation
- OpenAI: For building agents using its LLMs
- Sentence Transformer: To conduct embeddings
The Creating an application with Streamlit and AI agents section can be run on a CPU, but it would be preferred if it were run on a GPU.
The OpenAI library requires the use of an OpenAI token, and you should register with OpenAI to obtain it. The next sections can be run on CPUs and are mainly based on the use of the AsyncIO library. The code can be found on GitHub: https://github.com/PacktPublishing/Modern...
