Skip to content

Commit 9f0afc0

Browse files
authored
Merge pull request twitter#550 from MrAuro/improve-navi-docs
(docs): Improve README file for Navi
2 parents d1cab28 + 9115361 commit 9f0afc0

File tree

1 file changed

+8
-6
lines changed

1 file changed

+8
-6
lines changed

navi/navi/README.md navi/README.md

+8-6
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
# Navi: High-Performance Machine Learning Serving Server in Rust
22

3-
Navi is a high-performance, versatile machine learning serving server implemented in Rust, tailored for production usage. It's designed to efficiently serve within the Twitter tech stack, offering top-notch performance while focusing on core features.
3+
Navi is a high-performance, versatile machine learning serving server implemented in Rust and tailored for production usage. It's designed to efficiently serve within the Twitter tech stack, offering top-notch performance while focusing on core features.
44

55
## Key Features
66

@@ -23,12 +23,14 @@ While Navi's features may not be as comprehensive as its open-source counterpart
2323
- `thrift_bpr_adapter`: generated thrift code for BatchPredictionRequest
2424

2525
## Content
26-
We include all *.rs source code that makes up the main navi binaries for you to examine. The test and benchmark code, as well as configuration files are not included due to data security concerns.
26+
We have included all *.rs source code files that make up the main Navi binaries for you to examine. However, we have not included the test and benchmark code, as well as various configuration files, due to data security concerns.
2727

2828
## Run
29-
in navi/navi you can run. Note you need to create a models directory and create some versions, preferably using epoch time, e.g., 1679693908377
30-
- scripts/run_tf2.sh
31-
- scripts/run_onnx.sh
29+
In navi/navi, you can run the following commands:
30+
- `scripts/run_tf2.sh` for [TensorFlow](https://www.tensorflow.org/)
31+
- `scripts/run_onnx.sh` for [Onnx](https://onnx.ai/)
32+
33+
Do note that you need to create a models directory and create some versions, preferably using epoch time, e.g., `1679693908377`.
3234

3335
## Build
34-
you can adapt the above scripts to build using Cargo
36+
You can adapt the above scripts to build using Cargo.

0 commit comments

Comments
 (0)