Questions tagged [word-embedding]
For questions about word embedding, a language modelling technique in natural language processing. Questions can concern particular methods, such as Word2Vec, GloVe, FastText, etc, or word embeddings and their use in machine learning libraries in general.
1,112
questions
0
votes
0
answers
18
views
How to get multimodal embeddings from CLIP model?
I'm hoping to use CLIP to get a single embedding for rows of multimodal (image and text) data.
Say I have the following model:
from PIL import Image
import torch
from transformers import CLIPProcessor,...
-1
votes
0
answers
17
views
Models for getting similarity scores between categories and keywords [closed]
I want to get a similarity score between a category like vehicles and a list of words like headphone, water, truck, and green. The goal would be for each score to be low on words outside the category ...
-1
votes
1
answer
22
views
Recreating Text Embeddings From An Example Dataset
I have a list of sentences, and a list of their ideal embeddings on a 25-dimensional vector. I am trying to use a neural network to generate new encodings, but I am struggling. While the model runs ...
1
vote
0
answers
59
views
Is there a way to use CodeBERT to embed source code without natural language in input?
On CodeBERTS github they provide an example of using a NL-PL pair with the pretrained base model to create an embedding. I am looking to create an embedding using just source code which does not have ...
0
votes
0
answers
21
views
Small corpus, want to find associations. Word2Vec?
I'm a psychologist, and I'm diving into the field of AI. I could really use some help for a project. This semester, I discovered Word2Vec and was mesmerized by its capability to find associations. So, ...
0
votes
0
answers
48
views
Retreive a Metadata from the Chroma DB vector Store
I want to build a LLM application using Langchain, Ollama, RAG and Streamlit. My problem is: In streamlit application, after uploading the PDF, it takes so much time to generate and deliver the answer....
0
votes
1
answer
16
views
Calculation of document word vector in python. Sum or average word2vec?
I have some questions about generating a dissimilarity matrix of a bunch of text documents using word vectors. Here I tokenise the text, remove OOV and then sum the word vectors of each word to use as ...
1
vote
3
answers
83
views
Getting GloVe embeddings using gensim, triu not found in scipy.linalg
I am trying to build a sentiment analysing model, using the GloVe word embeddings...
I found multiple sources on how to import the embeddings into python, this one seemed to be the simplest...
Trying ...
0
votes
0
answers
72
views
Vector Embedding using Spark for compute
I have some large parquet files of data in Iceberg (which I have stored using Spark). My objective now is to pull these down using Spark, convert them into a spark dataframe, perform vector embedding ...
0
votes
0
answers
49
views
Question about encode_multi_process method of the SentenceTransformer
How can I leverage the encode_multi_process method of the SentenceTransformer class to encode a large list of sentences using multiple GPUs?
I tried using the encode_multi_process method of the ...
0
votes
0
answers
18
views
Skip-Gram Model description in word2vec explanation article
In his article word2vec Parameter Learning Explained Xin Rong says (page 7):
Each output is computed using the same hidden->output matrix:
Looking into the word2vec source code I don’t see any “...
1
vote
1
answer
187
views
Cannot access embeddings endpoint on vLLM hosting llama3-8b-instruct
I'm using vllm to run llama3-8b-instruct on a machine, I can access the chat endpoint, but when I access the embedding endpoint using following code I get NotFoundError: Error code: 404 - {'detail': '...
1
vote
1
answer
38
views
Fasttext pre-trained model is not producing OOV word vectors when using gensim downloader
I am having A LOT of trouble when trying to use all the fasttext libraries (in Jupyter with Anaconda3 on Windows 11) that I have found so far but this question is mainly about gensim's implementation. ...
1
vote
3
answers
179
views
"Deadline" error when embedding video with Google Vertex AI multimodal embedding modal
I am currently using Vertex AI's Multimodal Embedding Model (https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/get-multimodal-embeddings)
I was able to get the Image and Text examples ...
1
vote
0
answers
128
views
How to Convert HTML to Text Suitable for Vector Embedding Models
I would like to convert html files to plain text in a manner that preserves logical structuring of the html in terms of title <h1> subtitles <h2> sub sub titles <h3> and let's not ...