1,434 questions
0
votes
0
answers
68
views
Low cosine similarity score when using Langchain FAISS wrapper and CLIP Model
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 ...
- 21
Tooling
0
votes
2
replies
68
views
Speaker identification/ IVR detection in Indian telephony-calls along with real-time speaker count
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 ...
Best practices
0
votes
0
replies
57
views
Best way to generate embeddings for structured product attributes in B2B ecommerce search?
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
...
- 21
0
votes
0
answers
462
views
Problems using local OLLAMA during embedding to ChromaDB
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 ...
0
votes
0
answers
985
views
How to fix EOF Server Ollama Error when embedding
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/...
- 335
2
votes
4
answers
155
views
Loading many PyTorch .pt files from Google Drive in Google Colab is extremely slow
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 ...
- 21
3
votes
2
answers
218
views
Multimodal embedding requires video first, then image - why?
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 ...
- 76
-1
votes
1
answer
86
views
How to reconstruct sentences from mean-pooled embeddings (embedding inversion) [closed]
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 ...
1
vote
2
answers
664
views
How can I match the token count used by BGE-M3 embedding model before embedding?
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 ...
0
votes
0
answers
62
views
itext 5.5 add mp4 video
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
...
1
vote
1
answer
325
views
Rapidfuzz giving no matches but Fuzzywuzzy does
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, ...
0
votes
0
answers
185
views
Embed Android.Views.View in .net maui
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 ...
- 104
0
votes
0
answers
601
views
Qdrant 400 Bad Request Error When Inserting Multi-Vector Embeddings with Larger Batch Sizes via API
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 ...
1
vote
1
answer
231
views
Spring-AI embedding, cannot search result by method 'similaritySearching' [closed]
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-...
- 19
0
votes
1
answer
187
views
How to validate search terms when using embedding to look for objects in images
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 ...
- 2,758