Closed alew3 closed 3 weeks ago
OK, fixed most errors by running the script below, maybe it should be included in the setup script?
import nltk
nltk.download('stopwords')
but still got this error:
Traceback (most recent call last):
File "/home/ale/projects/HippoRAG/src/colbertv2_indexing.py", line 41, in <module>
kb_phrase_dict = pickle.load(open(args.phrase, 'rb'))
FileNotFoundError: [Errno 2] No such file or directory: 'output/sample_facts_and_sim_graph_phrase_dict_ents_only_lower_preprocess_ner.v3.subset.p'
Could you follow NLTK instructions:
Resource stopwords not found. Please use the NLTK Downloader to obtain the resource: >>> import nltk >>> nltk.download('stopwords')
And then see if there is still another problem? Thanks.
I replied above, fixed most errors, but still didn't run till the end.
got it working by deleting everything and starting again and using the specific model of turbo gpt as in the example, it was using the llm model name in the filename for some reason.
System: Ubuntu 23.04 / Nvidia Titan RTX GPU NVidia Driver Version: 550.78 CUDA Version: 12.4
trying to run the example with Coulbert
I get all these file not found errors
when calling the retriever