AI in Music, Tools, Projects, and Discussions
Music and AI
- Collaboration between GPT and Bark for music creation
- “Bark is lit too” 🔥
AI Tools and Libraries
- pandas-ai library: https://github.com/gventuri/pandas-ai
- Issues with ChatOpenAI giving “Could not parse LLM output:” errors
- Code snippets for language chain helpers and embeddings utils:
- Scale.com for content language: https://scale.com/content-language
AI Models and Projects
- Cohere’s multilingual model
- Project idea for creating shortcuts to automate tasks
- Resources for creating charts/graphs from data, open-source “Chart-GPT” resources especially python based
- Implementing file search using Langchain’s drive connector
- Performance gains attributed to Rust vs Golang for HNSW algorithm
AI Discussions and Queries
- Issues with limited RAM on Repl on Replit
- Measuring recall for file search
- Tuning recall/speed for HNSW algorithm
- Learners’ discussion at 4pm
- Feedback on a new product for generating design from prompts using a design system
- Generative AI impact on graphic design and marketing
- Interviewing product designers and graphic designers in marketing agencies
AI Resources and Links
- LLM.report for dashboard of costs incurred while using OpenAI api’s: https://llm.report
- Ann-benchmarks for recall measurement: https://ann-benchmarks.com
- Twitter link for stable diffusion in graphic design: https://twitter.com/bohanhou1998/status/1652151502012837890?s=20
Links
The description and link can be mismatched because of extraction errors.
- https://github.com/gventuri/pandas-ai: Anyone has found any solution to ChatOpenAI giving “Could not parse LLM output:” errors?
- https://github.com/jerryjliu/llama_index/blob/590639a14dd7346b7f5cc00a21dd24ce0d35ae30/gpt_index/langchain_helpers/text_splitter.py#L240 and https://github.com/openai/openai-python/blob/c556584eff3b36c92278e6af62cfe02ebb68fb65/openai/embeddings_utils.py#L21 - Anyone has found any solution to ChatOpenAI giving “Could not parse LLM output:” errors?
- https://github.com/jerryjliu/llama_index/blob/590639a14dd7346b7f5cc00a21dd24ce0d35ae30/gpt_index/langchain_helpers/text_splitter.py#L240: This is a link to a specific line of code in a Python file on GitHub related to text splitting.
- https://github.com/openai/openai-python/blob/c556584eff3b36c92278e6af62cfe02ebb68fb65/openai/embeddings_utils.py#L21: This is a link to a specific line of code in a Python file on GitHub related to embeddings.
- https://scale.com/content-language: This is a link to a webpage discussing content language on the Scale website, which was referenced in a paper by OpenAI.
- https://github.com/openai/openai-python/blob/c556584eff3b36c92278e6af62cfe02ebb68fb65/openai/embeddings_utils.py#L21: This link leads to the embeddings_utils.py file in the openai-python repository on GitHub. The message mentions that this code was used in OpenAI’s RLHF paper. Another link to the Scale website and a tweet by Misbah Sy are also provided.
- https://scale.com/content-language - OpenAI used this in their RLHF paper.
- The recall measurement details can be found at https://ann-benchmarks.com, in response to a question about how to read it. Another question in the same message asks for advice on implementing a semantic file search, potentially for use with Google Drive.
- https://llm.report: a tool that shows a nice dashboard of costs incurred while using OpenAI api’s, mentioned in a message thanking participants for sharing pointers and notes.
- https://twitter.com/bohanhou1998/status/1652151502012837890?s=20 - Looking to connect with graphic designers in marketing agencies or anyone who knows someone in such an agency.