Samuel Seng
Hey thanks for sharing this work! And I really appreciate the in depth beginner friendly blog post! I was wondering if this pseudocode was 1. Correct 2. Helpful to anyone...
Switches back to the GPT2 512 model that was used for the demo on the README. While slower, the results match the quality of the README's demo. | Current (distilgpt2_64_6)...
Adds support for using ollama as the LLM. Test Plan: OPENAI_API_KEY=none CHAT_MODEL="llama3.2:1b" CHAT_MODEL_BASE_URL=http://127.0.0.1:11434/v1 OLLAMA_EMBEDDING_MODEL="llama3.2:1b" poetry run python run.py "What is the price of AAPL?" Fixes: https://github.com/OpenBB-finance/openbb-agents/issues/29