Questions tagged [vector-database]
The vector-database tag has no summary.
10 questions
4 votes
1 answer
108 views
What Vector Database is purposed for large data?
I have few hundred millions embeddings with dimensions 512 and 768. I looking for vector DB that could run similarity search enough fast and with high precision. I don't want to use server with GPU, ...
- 41
2 votes
0 answers
37 views
in RAG, for large dataset, which similarity works? Why? how to handle problem with size of matrix in cosine similarity?
If we want to implement RAG for large dataset, which similarity works? Why? Also, how to handle problem with size of matrix in cosine similarity?
- 1,906
1 vote
0 answers
31 views
RAG System Design: Context-Aware Customer Support for Property Management with Mixed Property-Specific and Global Information
Background I manage a property portfolio on platforms like Airbnb, handling customer support through the entire guest journey (pre-booking to post-stay). I'm building a RAG system to help automate ...
- 111
0 votes
0 answers
38 views
book_instance: Book = Book(Book.csv) AttributeError: type object 'Book' has no attribute 'csv'
I am trying to create a vector database using Python. I have this dataset in a CSV file: ...
2 votes
1 answer
59 views
Retrieving products based on pre-existing filters, the fastest way possible
Introduction and case scenario I am developing a microservice for our project, which is going to handle a section named 'custom categories'. The scenario for this part is this: 1- Define the custom ...
- 123
0 votes
0 answers
51 views
How to Vectorise data
I have a set of data points that have various attributes (product, geography, unit, date). I then have incoming data with the same attributes. I want to vectorise my data set to find the closeness of ...
- 1
1 vote
0 answers
41 views
"text" parameter in pinecone call from langchain
In this tutorial, I do not understand what "text" refers to vectorstore = Pinecone(index, embeddings.embed_query, "text") Could you please help?...
- 49
0 votes
1 answer
1k views
What is the use of using Vector databases over Pandas Dataframes?
My question is why can't we use a pandas dataframe to do all the data retrieval? Can someone give reasons apart from the fact that databases has the persistence of Data?
18 votes
3 answers
9k views
How do vector databases work (for the lay-coder)?
A vector database is a type of database that stores and manages unstructured data, such as text, images, or audio, in vector embeddings (high-dimensional vectors) to make it easy to find and retrieve ...
0 votes
0 answers
900 views
Is it a problem to store your vector database in memory?
I'm learning ChatGPT/LLM Development and am regularly coming across all different kinds of vector database implementations. Some of them, e.g. Chroma, currently only support in-memory implementations ...
- 318