272 questions
Advice
1
vote
1
replies
36
views
RAG with Pinecone + GPT-5 for generating new math problems: incoherent outputs, mixed chunks, and lack of originality
I’m building a tool that generates new mathematics exam problems using an internal database of past problems.
My current setup uses a RAG pipeline, Pinecone as the vector database, and GPT-5 as the ...
1
vote
0
answers
39
views
Redis- OpenAI not able to tune with actual radis text retrieved from vector index
I am trying to create a simple vector index for conversation AI application where i want to use radis as long-term memory.
i configured radis locally and created the index which ideally stores
"...
- 11
0
votes
0
answers
28
views
RAG Pipeline Memory Leak - Vector Embeddings Not Releasing After Context Switch in Memo AI
Question:
I'm building a memory-augmented AI system using RAG with persistent vector storage, but facing memory leaks and context contamination between sessions.
Problem:
Vector embeddings aren't ...
0
votes
0
answers
207
views
Chroma.from_documents() hangs indefinitely when loading documents split by newline
I'm working with LangChain and trying to create a vector database from a text file containing book descriptions and ISBNs. Each line in the text file is a separate book description, so I split the ...
- 11
0
votes
1
answer
79
views
MUVERA compression not working with text2colbert-jinaai in Weaviate
I'm trying to use MUVERA compression with Jina ColBERT v2 embeddings in Weaviate, following the official documentation. However, MUVERA compression is not being applied: I'm still getting raw multi-...
- 351
0
votes
1
answer
42
views
Vector Search Puzzle: How to efficiently find the least similar documents?
I'm looking for advice on a vector search problem that goes against the grain of standard similarity searches.
What I have: I'm using Genkit with a vector database (Firestore) that's populated with ...
- 2,255
1
vote
1
answer
329
views
How to define a payload schema for a collection in Qdrant (Cluster UI)?
I'm using Qdrant in a cluster setup and want to define a payload_schema for a collection. I want to ensure that the structure of my payload is recognized and listed in the collection metadata.
Here’s ...
- 47
0
votes
0
answers
43
views
multi-intent queries in vector database retrieval
I'm working on a RAG pipeline using a vector database to search over a Q&A dataset. I'm using embedding-based dense retrieval to fetch relevant answers to user queries.
The issue I'm facing is ...
0
votes
0
answers
470
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 ...
0
votes
0
answers
120
views
Chromadb gives an error InvalidDimensionException: Embedding dimension 384 does not match collection dimensionality 768
This one is weird to me as I did create the embeddings with text model 004.
I persisted the database and had to zip it and upload it to hugging face utilizing git LFS.
I planned on unzipping that ...
- 1
1
vote
0
answers
60
views
Nprobe in Milvus, from filtered clusters?
In Milvus, with an IVF Flat Index, I understand that nlist clusters are made on the whole index. Now If I make a query with highly selective metadata filtering, will Milvus choose nprobe clusters from ...
- 63
0
votes
1
answer
66
views
Precision used in ChromaDB Index
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 ...
- 13
0
votes
2
answers
217
views
Can't get UUID from similarity search Weaviate
I tried to retrieve documents with similar content to later modify them, but when it came to updating, I realized I couldn't get the ID to update these documents.
Here’s the function I was using to ...
0
votes
1
answer
538
views
How to Retrieve Vector Store ID in Azure AI Search for RAG Pipeline?
I am working on a Retrieval-Augmented Generation (RAG) pipeline and need to attach my documents to an Azure OpenAI Assistant. I have followed these steps:
Processed Documents: Extracted text and ...
0
votes
0
answers
37
views
Why does total_rows and indexed_rows keep increasing with repeated upserts in Milvus when using the same data?
I’m testing Milvus upsert functionality with 1,000 records. Here’s my workflow:
Create a collection
Insert data (1,000 records)
Flush the data
Create an HNSW index
Observe the collection stats:
...
- 99