Skip to main content

All Questions

Tagged with
1 vote
0 answers
59 views

word/ sentence similarities

I am trying to find if a given word/ set of words are similar to a definition. Example - Definition - "vegetarian User" Now, if I want to check a set of sentences like below sentences = ['...
A3006's user avatar
  • 1,081
-1 votes
1 answer
49 views

Python Farm-haystack Dependencies

i am trying to implement a model using farm-haystack, however am having a dependency mismatch for the following libraries : transformers farm-haystack langchain pydantic fastapi uvicorn elasticsearch ...
Gee's user avatar
  • 1
0 votes
0 answers
40 views

How to pass AzureOpenAIEmbeddings in CrewAI, I don't have api keys I use azure_ad_token?

How to pass AzureOpenAIEmbeddings, I don't have api keys I use azure_ad_token? from langchain_openai.embeddings import AzureOpenAIEmbeddings azure_embeddings = AzureOpenAIEmbeddings( ...
MAC's user avatar
  • 1,546
1 vote
1 answer
38 views

TypeError: isinstance() arg 2 must be a type or tuple of types with collections search in Weaviate

I have the following code: from weaviate.classes.query import MetadataQuery import weaviate from langchain_huggingface import HuggingFaceEmbeddings embedding_model = HuggingFaceEmbeddings(model_name =...
Inkyu Kim's user avatar
  • 155
0 votes
1 answer
53 views

getting an error: object of type 'float' has no len()

I am a naive in python and started learning python few months ago I am working on twitter data in my local, it has 4 columns. ID, brand, sentiment, comment def data_clean_pipeline(text): #removing ...
a_mittal's user avatar
0 votes
0 answers
256 views

Why does moving ML model initialization into a function prevent GPU OOM errors when del, gc.collect(), and torch.cuda.empty_cache() fail?

for model_name in model_list: model = LLM(model_name, trust_remote_code=True) results = evaluate_model(model, task) del model gc.collect() torch.cuda.empty_cache() Despite ...
Charlie Parker's user avatar
1 vote
1 answer
94 views

How to use Hugging Face model with 512 max tokens on longer text (for Named Entity Recognition)

I have been using the Named Entity Recognition (NER) model https://huggingface.co/cahya/bert-base-indonesian-NER on Indonesian text as follows: text = "..." model_name = "cahya/bert-...
Mauro Escudero's user avatar
4 votes
1 answer
4k views

TypeError: ForwardRef._evaluate() missing 1 required keyword-only argument: 'recursive_guard'

Pls help. I need help setting up spacy inside jupyter enviornment I am trying to use spacy to summarize youtube transcripts but finding lots of problems with spacy and python 3.12.4/3.12.3. I started ...
frankr6591's user avatar
  • 1,267
0 votes
0 answers
36 views

Spacy hanging for badly formatted texts

I am using spacy (https://spacy.io/usage/spacy-101) with the "en_core_web_sm" model to chunk lots of documents using sentence detection (sentor component). The documents have no structure ...
lightning_missile's user avatar
0 votes
1 answer
386 views

Do I need to use Named Entity Recognition (NER) in tokenization?

I am working on an NLP project for sentiment analysis. I am using SpaCy to tokenize sentences. As I was reading the documentation, I learned about NER. I've read that it can be used to extract ...
LoukasPap's user avatar
  • 1,379
0 votes
0 answers
97 views

Python Rasa train not compatible with M3 Apple

Unable to run the "rasa train" in mac m3 terminal.. giving below error. 2024-06-26 17:27:12 INFO rasa.cli.train - Started validating domain and training data... zsh: illegal hardware ...
Shamil's user avatar
  • 736
0 votes
0 answers
22 views

Trying to read a .wav file but was able to convert only 20s conversation

I am trying to read a .wav file but was able to convert only 20s conversation into text. # code to read .wav file import speech_recognition as sr r = sr.Recognizer() audio = r"D:\...
Archita Singh's user avatar
0 votes
0 answers
536 views

pydantic has been upgraded from 1.10.13 to version 2.7.1. How to modify the following code?

from pydantic.schema import model_schema @classmethod def create_prompt( cls, tools: Sequence[BaseTool], prompt: str = None, input_variables: ...
xqxls's user avatar
  • 1
0 votes
0 answers
33 views

Why am I encountering a PocketSphinx Python Initialization Error on google colab

I am trying to use PocketSphinx to extract Phonemes from WAV audio files in google colab. I am initizialising PockerSphinx through a directory in my google drive. This is the code: sys.path.append('/...
Aarav Minocha's user avatar
0 votes
2 answers
329 views

Extracting only technical keywords from a text using RAKE library in Python

I want to use rake to extract technical keywords from a job description that I've found on Linkedin, which looks like this: input = "In-depth understanding of the Python software development ...
Fatemeh's user avatar

15 30 50 per page
1
2 3 4 5
85