143 questions
- Bountied 0
- Unanswered
- Frequent
- Score
- Trending
- Week
- Month
- Unanswered (my tags)
Advice
3
votes
0
replies
104
views
How can I efficiently run a RAG pipeline fully in Node.js using OpenAI embeddings and FAISS without relying on Python?
I am working with a small Retrieval-Augmented Generation (RAG) setup and I want to run the entire pipeline purely in Node.js without using any Python-based services.
Workflow I am going to follow :
...
1
vote
0
answers
75
views
RAG Chatbot does not answer paraphrased questions
I built a RAG chatbot in python,langchain, and FAISS for the vectorstore.
And the data is stored as JSON.
The chatbot sometimes refuses to answer when a question is rephrased.
Here are two ...
0
votes
0
answers
31
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 ...
2
votes
1
answer
216
views
Why is FAISS document retrieval slow and inconsistent on EC2 t3.micro instance?
I'm building a document Q&A system using FAISS for vector search on an AWS EC2 t3.micro instance (1 vCPU, 1GB RAM). My FAISS index is relatively small (8.4MB .faiss + 1.4MB .pkl files), but I'm ...
-1
votes
1
answer
55
views
How to ensure all documents contribute to summary context after merging indexes?
I'm building a LangChain RAG pipeline using the FAISS vector store. I'm merging multiple FAISS indexes — each representing one document — and then querying them to generate summaries or answers via ...
0
votes
0
answers
78
views
Error running faiss on Google cloud run but not on local
I get this error when I try to access the ntotal property on my faiss_index while running on Google Cloud Run.
\> "in method 'Index_ntotal_get', argument 1 of type 'faiss::Index *'"
This ...
0
votes
1
answer
53
views
problem with prompting using FAISS as a vector store to classify dialogs based on sentiment emotions
I have a .csv dataset consisting of text dialog between two people and the rating of the related emaotions:
| Text_Dialog | joy | anger | sad | happy |
|--------------------|-----|-------|-----|...
0
votes
0
answers
132
views
Optimise FAISS vector search results
I am using FAISS vector search to search across about 6 million data present in different vectors and then on top that results I am using fuzzysearch to filter out the top results.
The problem here is ...
1
vote
0
answers
414
views
FAISS.from_texts() occur ValueError: input not a numpy array
vec_multi = embedding.embed_documents(pdf_chunks)
import numpy as np
vec_np = np.array(vec_multi)
print(vec_np.shape) # (문장 개수, 임베딩 차원)
print(vec_np.dtype)
(2119, 768)
float64
...
1
vote
0
answers
88
views
Add new field in existing FAISS vector store
I have a csv file containing multiple fields and from that I am only adding the first_name & last_name and making unique id using uuid to the vectorstore. I want to add one more field from my csv ...
1
vote
1
answer
71
views
Index type 0x73726576 ("vers") not recognized
I have a chat bot app that I can run without any problem in my local environment.
I can both run it locally on pycharm and I can run a docker container locally again. then I deploy it to koyeb using ...
0
votes
1
answer
272
views
The FAISS indexing and the dataset indexing don't match
I'm trying to compute the recall after performing a HNSW search in FAISS. By recall, I mean the following metric:
Recall = TP / (TP + FN)
Where I consider an image as a True Positive (TP) if it ...
0
votes
1
answer
567
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
1
answer
481
views
FAISS Db Vector Search
I am combining two embeddings and both are numerical embeddings both having shape (1,1)
combined_embeddings = np.hstack((price_embeddings, location_embeddings))
index = faiss.IndexFlatL2(...
0
votes
0
answers
136
views
Merge multiple FAISS chunks in a single chunk
I have loaded data in FAISS using the chunks as my data was very large. So, after the process 110 chunks have been made with respective .faiss & .pkl files. I have written this code
import faiss
...