Skip to main content
1,438 questions
Newest Active Bountied Unanswered
Filter by
Sorted by
Tagged with
0 votes
0 answers
43 views

I am currently using Langchain wrapper of FAISS vector store and CLIP model. Since Langchain wrapper of FAISS supports only text embedding models, I have implemented my own embedding class(using ...
Aashishkumar's user avatar
  • 1
Tooling
0 votes
2 replies
60 views

I’m working on a Python pipeline for Indian telephony call recordings (mostly 8kHz mono, noisy, multilingual, and with mixed accents). I need to: estimate how many speakers are in the call run speaker ...
Nandini Singhal's user avatar
  • 1
Best practices
0 votes
0 replies
53 views

I am building a B2B product search system using vector embeddings and would like advice specifically on how to generate embeddings for structured product attributes. Context Domain: B2B ecommerce ...
Sumit Raj's user avatar
  • 21
0 votes
0 answers
365 views

I am running a Python script on a Linux VM without CUDA support and a local OLLAMA. When checking OLLAMA on the console with ollama run jina/jina-embeddings-v2-base-de "Hello world" the ...
Lars Hinrichsen's user avatar
  • 63
0 votes
0 answers
719 views

I built the RAG system in Laravel with Neuron AI framework. I tried to store docs to the vectorstore but I got error: [2025-12-04 06:49:45] local.ERROR: Server error: `POST http://localhost:11434/api/...
Leslie Joe's user avatar
  • 335
2 votes
4 answers
134 views

I am storing my ESM protein embeddings as individual .pt files in Google Drive (about 46,000 files, total size ~182 MB). When I try to load them in Google Colab, the process is extremely slow (only ~2 ...
Max__08's user avatar
  • 21
3 votes
2 answers
213 views

I am working with OmniEmbed model (https://huggingface.co/Tevatron/OmniEmbed-v0.1), which is built on Qwen2.5 7B. My goal is to get a multimodal embedding for images and videos. I have the following ...
n_arch's user avatar
  • 76
-1 votes
1 answer
80 views

I’m working on a research problem where I want to reconstruct or paraphrase sentences starting from synthetic embeddings. The embeddings are global (mean-pooled), not token-level, so they lose ...
melissa mattos's user avatar
  • 1
1 vote
2 answers
620 views

For my particular project, it would be very helpful to know how many tokens the BGE-M3 embedding model would break a string down into before I embed the text. I could embed the string and count the ...
ManBearPigeon's user avatar
  • 13
0 votes
0 answers
59 views

Is it possible to add mp4 videos to itet 5.5 and let them play upon showing? What I tried: final PdfPCell cell = new PdfPCell(); final Chunk chunk = new Chunk(); chunk.setAnnotation(PdfAnnotation ...
Mani Afschar Yazdi's user avatar
  • 43
1 vote
1 answer
277 views

I have been developing a matching system which matches the rows of the client and our central database depending on similarity. I have used a hybrid approach where I needed to somehow map the Company, ...
Prabhjit Singh's user avatar
  • 21
0 votes
0 answers
94 views

In transformer models, I've noticed that token embeddings and positional embeddings are added together before being passed into the attention layers: import torch import torch.nn as nn class ...
Yilmaz's user avatar
  • 51.4k
0 votes
0 answers
166 views

I want to use open AI to get embeddings for a recommendation system. I used my credentials everything worked. Now I need to use my company's credentials to get embeddings for the whole dataset, ...
Anna Abrahamyan's user avatar
  • 1
0 votes
0 answers
67 views

I want to embed an iframe that contains a vimeo video inside a container div and give that div any ole aspect-ratio and just have my vimeo video conform to that using something like object-fit: cover (...
taber's user avatar
  • 3,240
0 votes
0 answers
178 views

I'm migrating a project from android native to .net maui, by replacing native forms with embedded maui views (following the embedding method described in this MSDN page) However, now I'm facing a ...
Jesoo's user avatar
  • 104
0 votes
0 answers
582 views

Context I am working on a semantic search application and using Qdrant to store three types of embeddings per document: Dense embeddings (from OpenAI) Sparse embeddings (from Qdrant/BM25) Rerank ...
Himanshu Gupta's user avatar
  • 1
0 votes
0 answers
77 views

I tried to improve XGBoost by stacking node2vec embeddings to the original features for fraud detection. In literature and papers this is frequently discussed as a good method to enhance prediction ...
Marlon Brando's user avatar
  • 191
1 vote
1 answer
218 views

I'm using Spring ai to build an app, the stack I chose is jdk 21, spring-boot 3.3.11 ,spring-ai 1.0.0M6. And for both embedding and chat models, I chose to use Ollama, thus the spring-ai-ollama-spring-...
xiong's user avatar
  • 19
0 votes
1 answer
186 views

I have a search on my site that does both tradition full text search and searches using embeddings. So, for example, when you search 'red balloon' I want both the text and image results. The problem ...
Frank Conry's user avatar
  • 2,758
-1 votes
1 answer
29 views

i have looked at some gtk3 based desktop, used msys2 mingw and some possibly reactos or windows sdk code.Got the taskbar, clock and desktop replicated.. See it here: https://gitlab.com/bluedxca93/11-...
user43787's user avatar
  • 101
1 vote
1 answer
142 views

What is the format of node features that graph2vec and GL2vec in karateclub require? It does mention that there should be no string features but with or without it I am running into an error with the ...
Arindam Ghosh's user avatar
  • 133
0 votes
0 answers
93 views

Im training a model and in the first training, no matter how many epochs (10,20,30…) i trained the model, everything looks great! the acc was increasing and the loss was decreasing as well. but when i ...
LOYINuts's user avatar
  • 9
0 votes
1 answer
77 views

I am using BAAI/bge-large-en-v1.5 model to embed and then store these embeddings in ChromaDB vector-store. These embeddings are in the memory and using HNSW indexing. Is there a way I can find out the ...
Jarvis's user avatar
  • 13
0 votes
1 answer
98 views

I'm trying to load a local embedding model for a RAG system using LLama-index using Settings.embed_model="local:./models/multilingual-e5-large/" The path is correct, the embedding model was ...
Carl Brendt's user avatar
  • 11
-1 votes
2 answers
132 views

Background I'm developing an application that uses vector embeddings for similarity search. I'm considering storing these embeddings directly in Firestore documents, but I'm concerned about potential ...
Shajeel Afzal's user avatar
  • 5,943
0 votes
1 answer
64 views

I try to have a table visible for multiple questions on multiple qualtrics pages one after the other. I followed guidelines here: https://community.qualtrics.com/custom-code-12/pin-instructions-to-top-...
canIchangethis's user avatar
  • 253
0 votes
1 answer
68 views

I want to build a GUI to view matplotlib figures with forward and backward buttons. GUI is just similar to view images. To an extent, I could get the results I need. The problem is: that when I use ...
pranjal's user avatar
  • 1
2 votes
3 answers
3k views

In the embedding models documentation, the suggested way to generated embeddings is ollama.embeddings({ model: 'mxbai-embed-large', prompt: 'Llamas are members of the camelid family', }) but ...
punkish's user avatar
  • 15.7k
0 votes
1 answer
58 views

I’m facing an issue embedding a Kaltura video in a Sitecore rich text field. The video works perfectly in a standalone HTML file, but it doesn’t load when added to Sitecore. Here’s the code I’m using: ...
Saurabh Patil's user avatar
  • 1
0 votes
1 answer
127 views

Am new to Ontotext. I understand similarity index of ontotext. It creates vectors of the index data and we can do search upon it. Is there a way to create vectors by other embedding models? Please ...
Vanaja Uthayakumar's user avatar
  • 1
0 votes
1 answer
403 views

I am using Azure Search AI service to store my documents chunk along with some information inside the metadata. However when I try to filter on metadata the filter does not work. Here is an example of ...
Jason_mils's user avatar
  • 97
1 vote
0 answers
62 views

My data can be represented as a sequence of events; each event is a set of elements. Events appear one-by-one in time; elements appear all together within the event. Example: event_t1: {A, B, C}, ...
Yury Gubman's user avatar
  • 65
1 vote
1 answer
173 views

I am trying to implement the code discussed in the HuggingFace cookbook article at https://huggingface.co/learn/cookbook/en/rag_llamaindex_librarian. I get to the point where I am trying to install ...
Mark Hamilton's user avatar
  • 11
2 votes
5 answers
204 views

I need to execute some python and C at the same time. I tried using Python.h: #include <Python.h> int python_program(char* cwd) { char* python_file_path; FILE* fd; int run; ...
Yuki's user avatar
  • 93
0 votes
1 answer
126 views

I am attempting to create a CNN model for text classification based on tweet data with the ELMo embedding. Once the model is built before compiling I am issuing a model summary but the model summary ...
leakie's user avatar
  • 1
0 votes
0 answers
862 views

I have tried to convert hf model to gguf, and then import into ollama. But I got some problem. When I tried model like m3e-large (https://huggingface.co/moka-ai/m3e-large)，I successfully imported, ...
IronSpiderMan's user avatar
  • 48
1 vote
1 answer
357 views

Recently I learned about four-valued logic and the Catuṣkoṭi and I'm interested in applying these ideas to experiments with LLMs and embedding vectors. More specifically, given a large spectrum of ...
sigalor's user avatar
  • 1,439
0 votes
1 answer
327 views

I am creating a web application to display a graph created in Azure managed Grafana. I am trying to achieve this using the share->Embed option on the graph panel. It has been challenging. I have ...
KaiT's user avatar
  • 1
0 votes
1 answer
98 views

i am currently running the below python script: # Function to process MMR search def process_mmr_search(row, itemdesc): try: formatted_itemdesc = str(row[itemdesc]) print('...
Ashwin Baldawa's user avatar
  • 49
0 votes
2 answers
3k views

based on aws docs provided here , https://docs.aws.amazon.com/code-library/latest/ug/python_3_bedrock-runtime_code_examples.html. In the following example, a model in bedrock is invoked to generate ...
kishi's user avatar
  • 63
0 votes
2 answers
807 views

I'm using Vertex AI's TextEmbeddingModel to calculate embeddings, and the first call shows significantly higher latency than the rest, likely due to caching. However, this isn't context-caching, and ...
user1848018's user avatar
  • 1,116
0 votes
0 answers
184 views

My RAG pipeline (using Haystack) compiles and runs, but is returning empty responses. From my checks, I thought it might be due to the embedding and llm models not being compatible, so I changed to an ...
ArieAI's user avatar
  • 512
0 votes
1 answer
202 views

I'm currently trying to integrate Cohere embeddings into ChromaDB, but I'm facing an issue when adding documents to my Chroma collection. I am using chromadb 0.5.11 and cohere 5.10.0. When I use the ...
Marco Palombo's user avatar
  • 11
0 votes
1 answer
234 views

I'm having some trouble returning the score of a vector search on PostgreSQL. I have created a HNSW index on the columns answer_embedding and answer_keyword_embedding. In Python, I've written this ...
MrAssel's user avatar
  • 1
0 votes
1 answer
350 views

I am trying to embed a text using the langchain_aws BedrockEmbeddings, but when I invoke the function, I get a list with the None values. Here's the code: from langchain_community.llms.bedrock import ...
Md Tausif's user avatar
  • 521
0 votes
2 answers
157 views

I'm working on a C++ program depends on a C library that uses the "struct embedding" trick to simulate inheritance (of data storage, not behaviour), similar to the Parent and Child structs ...
Alexander's user avatar
  • 64k
0 votes
1 answer
854 views

I'm encountering a problem when trying to use inputs_embeds to pass the embedding to my model: ValueError: You passed `inputs_embeds` to `.generate()`, but the model class LlamaForCausalLM doesn't ...
Steven Thorn's user avatar
  • 1
0 votes
1 answer
472 views

I am using Colab, I am trying to import SentenceTransformer: from sentence_transformers import SentenceTransformer However, I got this error: ttributeError Traceback (most ...
A1iMansour's user avatar
  • 11
2 votes
0 answers
220 views

I am encountering an error while trying to instantiate the EmbeddingModel using the ONNX model intfloat/multilingual-e5-large. The error message is as follows: Failed to instantiate [org....
Zakaria Hd's user avatar
  • 21
2 votes
0 answers
706 views

I am trying to use ONNX export of model intfloat/multilingual-e5-large: https://huggingface.co/intfloat/multilingual-e5-large/tree/main/onnx I have successfully downloaded this model, using it ...
jirka's user avatar
  • 61

1
2 3 4 5
…
29