Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kanchishimono/python-faiss-grpc-server
Simple gRPC server for vector searching implemented by Python and Faiss
https://github.com/kanchishimono/python-faiss-grpc-server
ann anns approximate-nearest-neighbor-search faiss grpc grpc-server image-search nearest-neighbor-search python3 vector-search
Last synced: 2 months ago
JSON representation
Simple gRPC server for vector searching implemented by Python and Faiss
- Host: GitHub
- URL: https://github.com/kanchishimono/python-faiss-grpc-server
- Owner: KanchiShimono
- Created: 2020-09-10T07:27:10.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2020-12-26T10:14:34.000Z (about 4 years ago)
- Last Synced: 2023-03-12T01:51:43.611Z (almost 2 years ago)
- Topics: ann, anns, approximate-nearest-neighbor-search, faiss, grpc, grpc-server, image-search, nearest-neighbor-search, python3, vector-search
- Language: Python
- Homepage:
- Size: 24.4 KB
- Stars: 4
- Watchers: 1
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# python-faiss-grpc-server
[](https://github.com/KanchiShimono/python-faiss-grpc-server/actions?query=workflow%3ABuild)
Python gRPC server for apploximate nearest neighbor by [Faiss](https://github.com/facebookresearch/faiss).
## Installation
You can install as package by pip install on repository root.
```sh
pip install .
```
## Usage
You can start gRPC server by running following command.
```sh
python python/faiss_grpc/main.py
```
### Environment variable
Python Faiss gRPC server has some environment variables starts with prefix `FAISS_GRPC_`.
| Variable | Default | Description | Required |
| :------------------------- | :------ | :--------------------------------------------------------------------- | :------: |
| FAISS_GRPC_INDEX_PATH | - | Path to Faiss index | o |
| FAISS_GRPC_NORMALIZE_QUERY | False | Normalize query for search (This is useful to cosine distance metrics) | x |
| FAISS_GRPC_NPROBE | None | Faiss nprobe parameter | x |
| FAISS_GRPC_HOST | [::] | gRPC server host | x |
| FAISS_GRPC_PORT | 50051 | gRPC server listening port | x |
| FAISS_GRPC_MAX_WORKERS | 10 | Maximum number of gRPC server workers | x |
#### Support .env file
Python Faiss gRPC server supports `.env` file, above environment variables can specified like
```sh
# .env
FAISS_GRPC_INDEX_PATH=/path/to/index
FAISS_GRPC_NORMALIZE_QUERY=True
FAISS_GRPC_NPROBE=10
FAISS_GRPC_HOST=[::]
FAISS_GRPC_PORT=50051
FAISS_GRPC_MAX_WORKERS=2
```
## Examples
Client side code is under the `examples/client.py`.
You can run following command or directly running on interpreter.
```sh
cd examples
# show usage of client example
python client.py -h
# show heatbeat message
python client.py heatbeat
# search by query, get numer of neighbors given value (query is auto generated in command as identity vector)
python client.py search 10
# search by specified id, get numer of neighbors given value
python client.py search-by-id 0 10
```
## Development
### Generate python code
Following command will generate two python grpc code `faiss_pb2.py` and `faiss_pb2_grpc.py` under the `python/faiss_grpc/proto`.
If you update grpc definition `proto/faiss.proto`, you should regenerate at first.
```sh
make codegen
```
Then you have to fix import path in `faiss_pb2_grpc.py`.
```py
# Before
import faiss_pb2 as faiss__pb2
# After
import faiss_grpc.proto.faiss_pb2 as faiss__pb2
```
## Cautionary points
- Avoid to use SearchById on the index built by add_with_ids (can use from IndexIDMap, IndexIVF etc.). These index does not keep id complicatedly so reconstruct_n method may do unexpected behavior.
- Support only CPU index.
## Future work
- [ ] Prepare docker image
- [ ] Auto download index from remote location if `FAISS_GRPC_INDEX_PATH` was specified remote path