faiss Docker & Self-Hosted Deployment

GitHub

A library for efficient similarity search and clustering of dense vectors.

40,727 stars C++ C++ 1 file · ~9,385 tokens
1. Pull Image (DOCKERHUB) docker pull facebookresearch/faiss:latest
2. Docker Run (1-Click Launch) docker run -d --name faiss --restart always facebookresearch/faiss:latest
3. Podman Run podman run -d --name faiss --restart always facebookresearch/faiss:latest
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/facebookresearch/faiss:latest
5. ORAS Pull (OCI Artifact) oras pull facebookresearch/faiss:latest
faiss/cppcontrib/docker_dev/Dockerfile 
FROM ubuntu:22.04

RUN apt update && apt install -y python3 python3-pip gcc g++ mc git swig sudo libomp-dev libopenblas-dev wget libgflags-dev
RUN pip3 install numpy==1.26.4 scipy pytest
RUN cd /root && git clone https://github.com/facebookresearch/faiss
RUN wget -qO- "https://cmake.org/files/v3.26/cmake-3.26.5-linux-x86_64.tar.gz" | sudo tar --strip-components=1 -xz -C /usr/local
RUN cd /root/faiss && /usr/local/bin/cmake -B build -DFAISS_ENABLE_GPU=OFF -DBUILD_TESTING=ON -DCMAKE_BUILD_TYPE=Release .
RUN cd /root/faiss && make -C build -j 8 faiss
RUN cd /root/faiss && make -C build -j 8 swigfaiss
RUN cd /root/faiss/build/faiss/python && python3 setup.py install