Questions tagged [faiss]

77 questions
1
vote
1 answer

"StatusCode.UNAVAILABLE, internal: Milvus Proxy is not ready yet" - Milvus Vector Search Issue

Milvus was working fine for a while and I wanted to insert data. When I released the collection, milvus crashed with the error "StatusCode.UNAVAILABLE, internal: Milvus Proxy is not ready yet". I recreated the docker image several times and even…
1
vote
0 answers

Why are there occasional empty inner hits on nested kNN search?

I am having some issues using a nested kNN search. The problem is that occasionally, documents will be returned without any inner hits. How is this possible? Search result (notice the two last hits have empty inner hits): {'_shards': {'failed': 0,…
1
vote
0 answers

ValueError: substring not found when using autofaiss

Traceback (most recent call last): File "c:\Users\kaili\Documents\New folder (2)\x.py", line 5, in index, index_infos = build_index(embeddings, save_on_disk=False) File…
Nails
  • 11
  • 1
1
vote
0 answers

How to search knn in faiss with minimal distance > 0

I am performing a search in faiss, but sometimes the samples i query for are indexed, which is ok. But when querying for k nearest neighbors one of the returned samples is the queried sample. I can remove it post search but then I get k-1 samples…
1
vote
0 answers

Error in Faiss Kmeans Clustering of Images

I have a set of about 200 images that I want to cluster into groups of images with similar features. I'm using Resnet50 to extract feature vectors from images and with the help of Faiss Kmeans I'm trying to cluster them into groups. I have defined a…
Cressida
  • 94
  • 1
  • 9
0
votes
0 answers

How to create a vector index of only unique images in a large random image dataset using FAISS?

I have been following this blog post to create vector embeddings for a dataset of public domain images that I have downloaded from flickr. Everything is working as expected, I am able to search through the image dataset and find images most closely…
0
votes
1 answer

faiss vectore store delete using keys

i am trying to delete by filtering using metadata source by whrn i get to db.delete(list) i got NotImplementedError: delete method must be implemented by subclass. this is the code: db = FAISS.load_local(FAISS_USERGUIDE_INDEX, embeddings) def…
Hamza Dh
  • 1
  • 1
0
votes
1 answer

Multiple file loading and embeddings with OpenAI

I am trying to load a bunch of pdf files and query them using OpenAI APIs. from langchain.text_splitter import CharacterTextSplitter #from langchain.document_loaders import UnstructuredFileLoader from langchain.document_loaders import…
Soakland
  • 1
  • 1
0
votes
1 answer

Extract ProductQuantizer from FAISS IndexIVF

I'm trying to extract the pre-precessing part (OPQ) of my FAISS Index so that I can return the approximate vectors as part of my API response. Specifically, I am not able to extract the Product Quantizer from the Index. Code: import numpy as…
Guillaume
  • 1,277
  • 2
  • 13
  • 21
0
votes
0 answers

I want a suggestion to embed a large number of PDF into a Faiss Vector Store | Llama_Index | PDF reader

Actually I am trying to build a chat bot which can answer the questions from a set of pdf's. I use llama_index for retrival. The bot is working now without any issues. But the quality of the answers is not that great :( . I believe that is because I…
Nandha
  • 11
  • 1
0
votes
1 answer

Is `MongoDBAtlasVectorSearch` built upon `FAISS` algorithm?

I am using langchain for building softwares for pdf document reading and question-answering. While working on it, I have to build vector embeddings for the texts in the document. But while working on it, I have come across multiple platforms such as…
0
votes
1 answer

Python API documentation for FAISS

I am searching for a Python API documentation for FAISS, unable to find it. The wiki page says the python translation is very close to the C++ classes whose documentation can be found here
ChrisOdney
  • 6,066
  • 10
  • 38
  • 48
0
votes
0 answers

How to do clustering with langchain FAISS?

I'm trying to do clustering on my Faiss vector vector_store = FAISS.load_local("embeddings_of_songs", embeddings=embeddings) but all I found on google is faiss similarity_search I'm trying to do a kmeans clustering for vector_store, any help would…
0
votes
0 answers

Chatting with PDFs using Lang chain

''' bot.gpt_turbo = Model_LLM(OPENAI_DEPLOYMENT_NAME, openai.api_version).model embeddings = OpenAIEmbeddings(model=OPENAI_EMBEDDING_MODEL_NAME) fileLoaded = FileLoader("Data/filename.pdf", TokenTextSplitter(chunk_size=1000,…
0
votes
0 answers

faiss failed to find a target when running it with cmake

I run the following command to install faiss directly from source (I cloned https://github.com/facebookresearch/faiss) and once inside the folder I run: cmake -B build . I get the error below: -- The C compiler identification is GNU 9.4.0 --…
tmd13
  • 55
  • 2
  • 6