Stack Overflow
Stack Overflow

Questions tagged [vector-database]

Vector databases are purpose built databases specialized in storing and querying vector embeddings. They are primarily used when working with unstructured data in a way that calls for semantic comparison.

62 questions
4
votes
1 answer

What JPA + Hibernate data type should I use to support the vector extension in a PostgreSQL database?

What JPA + Hibernate data type should I use to support the vector extension in a PostgreSQL database, so that it allows me to create embeddings using a JPA Entity? CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3)); pgvector
user352290
  • 473
  • 1
  • 5
  • 16
3
votes
1 answer

How to improve/preprocess text (in special cases) so the embeddings and LLM will have better context?

I have been working on setting up local documents to be ingested into vectordb and then to be used (embeddings) as context for the LLM. Problem is, local documents are very much high level (check below more details). After it's chunked with…
Daniel Abhishek
  • 31
  • 3
3
votes
1 answer

How to deploy chroma database (vector database) in production

I am working on a project where i want to save the embeddings in vector database. need some help or resources to deploy chroma db for production use
ankitmhjn5
  • 89
  • 5
2
votes
0 answers

How to save vector embeddings `FAISS` in MongoDB?

I am using LangChain for building some stuff and came across one of the most prominent index-based vector database FAISS. Following is the command of how I am using the FAISS vector database: from langchain.document_loaders import PyMuPDFLoader from…
Shuhul Handoo
  • 122
  • 8
2
votes
0 answers

Unable to install pgvector extension for PostgreSQL [Windows]

I am trying to use PostgreSQL as a vector database. And for the same I installed PostgreSQL to my windows system using the instructions provided here. To install pgvector, I followed the instructions given in this page. I am trying to complete this…
Sai Kirtana G
  • 21
  • 2
2
votes
1 answer

How do you catch the duplicate id error when using langchain.vectorstores.Chroma.from_documents()

I use the following line to add langchain documents to a chroma database: Chroma.from_documents(docs, embeddings, ids=ids, persist_directory='db') when ids are duplicates, I get this error: chromadb.errors.IDAlreadyExistsError how do I catch the…
Suibhne
  • 21
  • 2
2
votes
1 answer

Embedding and Geo Filter Search in Redis

Does redis support geospatial and vector search like (knn) in the same query. I understand a simple filter query feeding into knn search like the one below would work "(@title:Matrix @year:[2020 2022])=>[KNN 10 @v $B]" I am curious if the filter…
user3221430
  • 71
  • 1
  • 6
2
votes
2 answers

How to find closest embedding vectors?

I have 100K known embedding i.e. [emb_1, emb_2, ..., emb_100000] Each of this embedding is derived from GPT-3 sentence embedding with dimension 2048. My task is given an embedding(embedding_new) find the closest 10 embedding from the above 100k…
Exploring
  • 2,493
  • 11
  • 56
  • 97
1
vote
0 answers

Looking for a ChromaDB Client Similar to pgAdmin or MongoDB Studio

I am currently working with ChromaDB for a project and I'm in need of a user-friendly client tool that can provide a graphical interface for managing and interacting with my ChromaDB instance. Much like pgAdmin for PostgreSQL and MongoDB Studio for…
Dinesh Sonachalam
  • 1,223
  • 19
  • 33
1
vote
1 answer

Install the correct onxruntime for chromadb with pip install

I am trying to install chromadb on my jupyter notebook (Anaconda) using: pip install chromadb I get error: ERROR: Could not find a version that satisfies the requirement onnxruntime>=1.14.1 (from chromadb) (from versions: 1.2.0, 1.3.0, 1.4.0,…
Victor
  • 16,609
  • 71
  • 229
  • 409
1
vote
1 answer

Optimizing Weaviate for Image Embedding Search without Storing Images

I’m currently working on a project where I’m using Weaviate as a vector database to store and search for images based on their embeddings. The images themselves are stored in an S3 bucket. My goal is to leverage Weaviate’s capabilities solely for…
Mansur
  • 182
  • 2
  • 8
1
vote
0 answers

use existing elasticsearch7/8 for vector search vs adding dedicated vector database

I already have elastic search engine installed and I want to add openai ada embedding for lexical similarity score support for better multilingual and synonyms in my application. Should I add a new vector database or just use existing elasticsearch…
djy
  • 737
  • 6
  • 14
1
vote
0 answers

How to create a vector database of huge set of enterprise documents?

This is a sort of a design question. I am VectorDB newbie. I am working on creating a LLM enable summarisation system for a huge set of documents. These documents will have a certain date in them. Users can be searching them on these dates. When the…
Tanmoy
  • 11
  • 2
1
vote
1 answer

embeddings and semantic search in spanish

I'm building an AI assistant that interacts with custom Q&A stored in a vector database. All examples of it shows as a very simple task of chunking documents (QA in this case), creating embeddings, storing them in a vector DB, and then querying when…
Cristian Sepulveda
  • 1,572
  • 1
  • 18
  • 25
1
vote
1 answer

Pinecone MaxRetryError and NewConnectionError

An application I've hosted online throws an error whenever it tries to query a pinecone database that I've set up. Whenever I run the same code (same pinecone environment and API key) on my local device, the queries go through just fine. Any ideas…
Jebbert
  • 13
  • 4
1
2 3 4