Closed FrankTseng168 closed 8 months ago
Same here. I face this error with the code for the quickstart paid model:
ImportError: cannot import name 'ALLOWED_NETLOCK' from 'langchain.document_loaders.youtube'
@FrankTseng168 @LouisMonierSpark this should be fixed in the next release! Please feel free to reach out if there is any other problem.
🐛 Describe the bug
config_huggingface = { 'llm': { 'provider': 'huggingface', 'config': { 'model': 'google/flan-t5-xxl', 'temperature': 0.7, 'max_tokens': 1000, 'top_p': 0.8, 'stream': False } }, 'embedder': { 'provider': 'huggingface', 'config': { 'model': 'sentence-transformers/all-mpnet-base-v2' } } }
import os from embedchain import Pipeline as App os.environ["HUGGINGFACE_ACCESS_TOKEN"] = ""
Create a bot instance
elon_bot = App.from_config(config=config_huggingface)
Embed online resources
elon_bot.add("https://en.wikipedia.org/wiki/Elon_Musk") elon_bot.add("https://www.forbes.com/profile/elon-musk")
Query the bot
elon_bot.query("How many companies does Elon Musk run and name those?")
Chat the bot
elon_bot.chat("How many companies does Elon Musk run and name those?")