Shawn Esquivel
Shawn Esquivel
im facing a similar issue with my scatter plots. I generate a 72MB file which always crashes when I try to open it in the browser.
Was your `OpenAIEmbeddings` `model` parameter OK with the default (text-embedding-ada-002)? Personally, I had to change model to "gpt2" as per #3811. ``` File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/tiktoken/registry.py", line 60, in get_encoding raise ValueError(f"Unknown...
Having this issue as well.
Changing to `tiktoken.encoding_for_model(self.model)` as you recommended gave me this error: AttributeError: module 'tiktoken' has no attribute 'encoding_for_model' tiktoken 0.1.2
Here is the constructor `__init__.py ` for tiktoken [source](https://github.com/openai/tiktoken/blob/main/tiktoken/__init__.py#L4) ``` from .core import Encoding as Encoding from .registry import get_encoding as get_encoding from .registry import list_encoding_names as list_encoding_names ``` Thus...
In summary, my proposed changes that made it work for me are: https://github.com/hwchase17/langchain/blob/master/langchain/embeddings/openai.py#L188 Change: `encoding = tiktoken.model.encoding_for_model(self.model)` https://github.com/hwchase17/langchain/blob/master/langchain/embeddings/openai.py#L107 Change: `model: str = "gpt2"`
@dmytrokarpovych There is an open PR that is somewhat related #3819 I don't think it incorporates the default model that I used though.
Hey @AaronWard Give this a try. It worked for me. https://stackoverflow.com/questions/68275857/urllib-error-urlerror-urlopen-error-ssl-certificate-verify-failed-certifica Let me know if it works.
@cygkichi Thanks that fixed it. But I'm still getting a NoTranscript Error. Is there a way to pass the language into the YoutubeLoader? ``` No transcripts were found for any...