Hugging Face's logo
xcu's picture

xcu

xcu

AI & ML interests

None yet

Recent Activity

replied to CultriX's post 1 day ago
Hi all! I was hoping somebody would be willing to check out this thought experiment of mine with the aim to reduce tokens in inter-agent communications. How It Works: 1. You provide a task in natural language (NL) 2. NL-to-CCL Agent: Converts your request into a structured Compressed Communication Language (CCL) task. 3. Inter-agent communication occurs in CCL 4. CCL is translated back to NL before being presented to the user. I have a notebook with an example that claims to achieve these results: --- Token Usage Summary --- Total NL Tokens (User Input & Final Output): 364 Total CCL Tokens (for NL/CCL Conversions): 159 Total CCL Tokens (Internal Agent Communication): 194 Overall token savings on NL-to-CCL conversion portions: 56.32% ------------------------ When asking Gemini it concludes: "Yes, the methods used in this notebook are sensible. The multi-agent architecture is logical, and the introduction of a Compressed Communication Language (CCL) is a clever and practical solution to the real-world problems of token cost and ambiguity in LLM-based systems. While it's a proof-of-concept that would need more robust error handling and potentially more complex feedback loops for a production environment, it successfully demonstrates a viable and efficient strategy for automating a software development lifecycle." However, I have no idea if it's actually working or if I'm just crazy. Would really like it if someone would be willing to provide thoughts on this! The notebook: https://gist.github.com/CultriX-Github/7f9895bc5e4d99d2d4a3eb17d079f08b#file-token-reduction-ipynb Thank you for taking the time! :)
replied to chunchu-08's post 2 days ago
## Issue Summary **Space:** [`chunchu-08/LLM-Comparison-Hub`](https://huggingface.co/spaces/chunchu-08/LLM-Comparison-Hub) **Hardware:** Paid CPU Upgrade (8 vCPU, 32 GB RAM) Free tier CPU- It worked fine two days ago but now it is not working either on free tier CPU or Paid CPU **Model:** `gpt-4` via `openai>=1.0.0` SDK **Error:** GPT-4 call works perfectly on local machine with same key: ```python from openai import OpenAI client = OpenAI(api_key=os.getenv("OPENAI_API_KEY")) client.chat.completions.create( model="gpt-4", messages=[{"role": "user", "content": "Hello GPT-4"}] ) Claude and Gemini models work fine in the same Space .env is loaded correctly using load_dotenv() No IP restrictions set on OpenAI key Logs just show Connection error. — no traceback What I’ve Tried Tested OPENAI_API_KEY locally — works Added logging using test_openai_connection.py Restarted Space and tested again Confirmed Claude/Gemini give valid outputs GPT-4 fails silently My Questions Has Hugging Face introduced outbound network restrictions to api.openai.com recently? Does even paid CPU Space share outbound IP pools that are rate-limited by OpenAI? Any recommended workaround? https://huggingface.co/huggingface @louie @nateraw @julien-c
View all activity

Organizations

None yet