But I guess main reason is, though I am using LLM from HuggngFaceHub, via Service Context, it is still searching for OpenAI
File "C:\Users\yoges\anaconda3\envs\langchain\Lib\site-packages\tenacity__init.py", line 382, in call__ result = fn(args, kwargs)^^^^^^^^^^^^^^^^^^^ File "C:\Users\yoges\anaconda3\envs\langchain\Lib\site-packages\llama_index\embeddings\openai.py", line 150, in get_embeddings data = openai.Embedding.create(input=list_of_text, model=engine, kwargs).data^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\yoges\anaconda3\envs\langchain\Lib\site-packages\openai\api_resources\embedding.py", line 33, in create response = super().create(args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\yoges\anaconda3\envs\langchain\Lib\site-packages\openai\api_resources\abstract\engine_apiresource.py", line 153, in create response, , api_key = requestor.request( ^^^^^^^^^^^^^^^^^^ File "C:\Users\yoges\anaconda3\envs\langchain\Lib\site-packages\openai\api_requestor.py", line 230, in request resp, got_stream = self._interpret_response(result, stream) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\yoges\anaconda3\envs\langchain\Lib\site-packages\openai\api_requestor.py", line 624, in _interpret_response self._interpret_response_line( File "C:\Users\yoges\anaconda3\envs\langchain\Lib\site-packages\openai\api_requestor.py", line 687, in _interpret_response_line raise self.handle_error_response( openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details. Now the error is being generated in langchain land, but the suggested version does not solve it
Following seems to work, so two models, one for LLMPredictor and one for embeding (by default its sentence transformer inside)... looks ok? @Logan M repo_id = "tiiuae/falcon-7b" embed_model = LangchainEmbedding(HuggingFaceEmbeddings())
