Change documentation links to point to release tag (#1624)

JIRA:CVS-98971

docs/accelerators.md

@@ -112,7 +112,7 @@ docker run --rm -it --device=/dev/dxg --volume /usr/lib/wsl:/usr/lib/wsl --grou
 > **NOTE**:
 > The public docker image includes the OpenCL drivers for GPU in version 22.28 (RedHat) and 22.35 (Ubuntu).
 
-If you need to build the OpenVINO Model Server with different driver version, refer to the [building from sources](https://github.com/openvinotoolkit/model_server/blob/develop/docs/build_from_source.md)
+If you need to build the OpenVINO Model Server with different driver version, refer to the [building from sources](https://github.com/openvinotoolkit/model_server/blob/v2022.3/docs/build_from_source.md)
 
 ## Using Multi-Device Plugin
 
@@ -232,7 +232,7 @@ The docker image of OpenVINO Model Server including support for NVIDIA can be bu
  cd model_server
  make docker_build NVIDIA=1 OV_USE_BINARY=0 OV_SOURCE_BRANCH=releases/2022/3 OV_CONTRIB_BRANCH=releases/2022/3
 ```
-Check also [building from sources](https://github.com/openvinotoolkit/model_server/blob/develop/docs/build_from_source.md).
+Check also [building from sources](https://github.com/openvinotoolkit/model_server/blob/v2022.3/docs/build_from_source.md).
 
 Example command to run container with NVIDIA support:
 

docs/binary_input_kfs.md

@@ -203,7 +203,7 @@ pip install -r requirements.txt
 ```
 
 ### Run the gRPC client sending JPEG images
-([see the code](https://github.com/openvinotoolkit/model_server/blob/develop/client/python/kserve-api/samples/grpc_infer_binary_resnet.py))
+([see the code](https://github.com/openvinotoolkit/model_server/blob/v2022.3/client/python/kserve-api/samples/grpc_infer_binary_resnet.py))
 ```bash
 python3 ./grpc_infer_binary_resnet.py --grpc_port 9000 --images_list resnet_input_images.txt --labels_numpy_path ../../lbs.npy --input_name 0 --output_name 1463 --model_name resnet
 Start processing:
@@ -253,7 +253,7 @@ Classification accuracy: 100.00
 
 
 ### Run the REST client sending JPEG images
-([see the code](https://github.com/openvinotoolkit/model_server/blob/develop/client/python/kserve-api/samples/http_infer_binary_resnet.py))
+([see the code](https://github.com/openvinotoolkit/model_server/blob/v2022.3/client/python/kserve-api/samples/http_infer_binary_resnet.py))
 ```bash
 python3 ./http_infer_binary_resnet.py --http_port 8000 --images_list resnet_input_images.txt --labels_numpy_path ../../lbs.npy --input_name 0 --output_name 1463 --model_name resnet
 Start processing:
@@ -302,7 +302,7 @@ Classification accuracy: 100.00
 ```
 
 ### Run the REST client with raw data sent in binary representation
-([see the code](https://github.com/openvinotoolkit/model_server/blob/develop/client/python/kserve-api/samples/http_infer_resnet.py))
+([see the code](https://github.com/openvinotoolkit/model_server/blob/v2022.3/client/python/kserve-api/samples/http_infer_resnet.py))
 ```bash
 python3 ./http_infer_resnet.py --http_port 8000 --images_numpy_path ../../imgs_nhwc.npy --labels_numpy_path ../../lbs.npy --input_name 0 --output_name 1463 --model_name resnet --transpose_input False --binary_data
 Image data range: 0.0 : 255.0

docs/binary_input_tfs.md

@@ -100,7 +100,7 @@ pip install -r requirements.txt
 ```
 
 ### Run the gRPC client sending the binary input
-([see the code](https://github.com/openvinotoolkit/model_server/blob/develop/client/python/ovmsclient/samples/grpc_predict_binary_resnet.py))
+([see the code](https://github.com/openvinotoolkit/model_server/blob/v2022.3/client/python/ovmsclient/samples/grpc_predict_binary_resnet.py))
 ```bash
 python grpc_predict_binary_resnet.py --images_dir ../../../../demos/common/static/images --model_name resnet --service_url localhost:9000
 Image ../../../../demos/common/static/images/magnetic_compass.jpeg has been classified as magnetic compass
@@ -117,7 +117,7 @@ Image ../../../../demos/common/static/images/golden_retriever.jpeg has been clas
 
 
 ### Run the REST client sending the binary input
-([see the code](https://github.com/openvinotoolkit/model_server/blob/develop/client/python/ovmsclient/samples/http_predict_binary_resnet.py))
+([see the code](https://github.com/openvinotoolkit/model_server/blob/v2022.3/client/python/ovmsclient/samples/http_predict_binary_resnet.py))
 ```bash
 python http_predict_binary_resnet.py --images_dir ../../../../demos/common/static/images --model_name resnet --service_url localhost:8000
 Image ../../../../demos/common/static/images/magnetic_compass.jpeg has been classified as magnetic compass

docs/build_from_source.md

@@ -126,4 +126,4 @@ Example:
 make docker_build OV_USE_BINARY=0 OV_SOURCE_BRANCH=<commit or branch>
 ```
 
-Read more detailed usage in [developer guide](https://github.com/openvinotoolkit/model_server/blob/develop/docs/developer_guide.md).
+Read more detailed usage in [developer guide](https://github.com/openvinotoolkit/model_server/blob/v2022.3/docs/developer_guide.md).

docs/clients_kfs.md

@@ -84,7 +84,7 @@ When creating a Python-based client application, you can use Triton client libra
 
 @endsphinxdirective
 
-For complete usage examples see [Kserve samples](https://github.com/openvinotoolkit/model_server/tree/develop/client/python/kserve-api/samples).
+For complete usage examples see [Kserve samples](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/python/kserve-api/samples).
 
 ## C++ Client
 
@@ -95,4 +95,4 @@ For complete usage examples see [Kserve samples](https://github.com/openvinotool
 
 Creating a client application in C++ follows the same principles as Python. When creating a C++-based client application, you can use Triton client library - [tritonclient](https://github.com/triton-inference-server/client).
 
-See our [C++ samples](https://github.com/openvinotoolkit/model_server/tree/develop/client/cpp/kserve-api/README.md) to learn how to build a sample C++ client application. 
+See our [C++ samples](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/cpp/kserve-api/README.md) to learn how to build a sample C++ client application. 

docs/metrics.md

@@ -221,7 +221,7 @@ It means that each request to the DAG pipeline will update also the metrics for
 
 With server metrics being scraped by [Prometheus](https://prometheus.io/) it is possible to integrate [Grafana](https://grafana.com/) to visualize them on the dashboards. Once you have Grafana configured with Prometheus as a data source, you can create your own dashboard or import one. 
 
-In OpenVINO Model Server repository you can find [grafana_dashboard.json](https://github.com/openvinotoolkit/model_server/blob/develop/extras/grafana_dashboard.json) file that can be used to visualize per model metrics like:
+In OpenVINO Model Server repository you can find [grafana_dashboard.json](https://github.com/openvinotoolkit/model_server/blob/v2022.3/extras/grafana_dashboard.json) file that can be used to visualize per model metrics like:
 - Throughput [RPS] - number of requests being processed by the model per second.
 - Mean Latency [ms] - latency averaged across all requests processed by the model in a certain timeframe.
 - Latency Quantile [ms] - value of latency for quantiles [0.75, 0.90, 0.99], meaning the latency that has NOT been exceeded by 75%, 90% and 99% of the requests.

docs/model_server_c_api.md

@@ -6,7 +6,7 @@ This document describes OpenVINO Model Server (OVMS) C API that allows OVMS to b
 
 ## API Description
 
-Server functionalities are encapsulated in shared library built from OVMS source. To include OVMS you need to link this library with your application and use C API defined in [header file](https://github.com/openvinotoolkit/model_server/blob/develop/src/ovms.h). 
+Server functionalities are encapsulated in shared library built from OVMS source. To include OVMS you need to link this library with your application and use C API defined in [header file](https://github.com/openvinotoolkit/model_server/blob/v2022.3/src/ovms.h). 
 
 
 To start model serving you need to spawn process that will keep OVMS alive. Then you can schedule inference both directly from app using C API and gRPC/HTTP endpoints.

docs/model_server_grpc_api_kfs.md

@@ -12,7 +12,7 @@ The API includes following endpoints:
 * <a href="#kfs-model-metadata">Model Metadata API </a>
 * <a href="#kfs-model-infer"> Inference API </a>
 
-> **NOTE**: Examples of using each of above endpoints can be found in [KServe samples](https://github.com/openvinotoolkit/model_server/tree/develop/client/python/kserve-api/samples/README.md).
+> **NOTE**: Examples of using each of above endpoints can be found in [KServe samples](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/python/kserve-api/samples/README.md).
 
 
 ## Server Live API <a name="kfs-server-live"></a>
@@ -51,7 +51,7 @@ Check [how binary data is handled in OpenVINO Model Server](./binary_input.md)
 
 ## See Also
 
-- [Example client code](https://github.com/openvinotoolkit/model_server/tree/develop/client/python/kserve-api/samples/README.md) shows how to use GRPC API and REST API.
+- [Example client code](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/python/kserve-api/samples/README.md) shows how to use GRPC API and REST API.
 - [KServe API](https://github.com/kserve/kserve/tree/master/docs/predict-api/v2)
 - [gRPC](https://grpc.io/)
 

docs/model_server_rest_api_kfs.md

@@ -36,7 +36,7 @@ Date: Tue, 09 Aug 2022 09:20:24 GMT
 Content-Length: 2
 ```
 
-See also [code samples](https://github.com/openvinotoolkit/model_server/tree/develop/client/python/kserve-api/samples) for getting server liveness with KServe API on HTTP Server Live endpoint.
+See also [code samples](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/python/kserve-api/samples) for getting server liveness with KServe API on HTTP Server Live endpoint.
 
 ## Server Ready API <a name="kfs-server-ready"></a>
 **Description**
@@ -63,7 +63,7 @@ Date: Tue, 09 Aug 2022 09:22:14 GMT
 Content-Length: 2
 ```
 
-See also [code samples](https://github.com/openvinotoolkit/model_server/tree/develop/client/python/kserve-api/samples) for getting server readiness with KServe API on HTTP Server Ready endpoint.
+See also [code samples](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/python/kserve-api/samples) for getting server readiness with KServe API on HTTP Server Ready endpoint.
 
 ## Server Metadata API <a name="kfs-server-metadata"></a>
 **Description**
@@ -103,7 +103,7 @@ $ curl http://localhost:5000/v2
 
 For detailed description of the response contents see [KServe API docs](https://github.com/kserve/kserve/blob/master/docs/predict-api/v2/required_api.md#server-metadata).
 
-See also [code samples](https://github.com/openvinotoolkit/model_server/tree/develop/client/python/kserve-api/samples) for getting server metadata with KServe API on HTTP Server Metadata endpoint.
+See also [code samples](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/python/kserve-api/samples) for getting server metadata with KServe API on HTTP Server Metadata endpoint.
 
 ## Model Ready API <a name="kfs-model-ready"></a>
 **Description**
@@ -130,7 +130,7 @@ Date: Tue, 09 Aug 2022 09:25:31 GMT
 Content-Length: 2
 ```
 
-See also [code samples](https://github.com/openvinotoolkit/model_server/tree/develop/client/python/kserve-api/samples) for getting model readiness with KServe API on HTTP Model Ready endpoint.
+See also [code samples](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/python/kserve-api/samples) for getting model readiness with KServe API on HTTP Model Ready endpoint.
 
 
 
@@ -185,7 +185,7 @@ $ curl http://localhost:8000/v2/models/resnet
 
 For detailed description of the response contents see [KServe API docs](https://github.com/kserve/kserve/blob/master/docs/predict-api/v2/required_api.md#model-metadata).
 
-See also [code samples](https://github.com/openvinotoolkit/model_server/tree/develop/client/python/kserve-api/samples) for running getting model metadata with KServe API on HTTP Model Metadata endpoint.
+See also [code samples](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/python/kserve-api/samples) for running getting model metadata with KServe API on HTTP Model Metadata endpoint.
 
 ## Inference API <a name="kfs-model-infer"></a>
 **Description**
@@ -285,4 +285,4 @@ For detailed description of request and response contents see [KServe API docs](
 
 > Note: More efficient way of running inference via REST is sending data in a binary format outside of the JSON object, by using [binary data extension](./binary_input_kfs.md). 
 
-See also [code samples](https://github.com/openvinotoolkit/model_server/tree/develop/client/python/kserve-api/samples) for running inference with KServe API on HTTP Inference endpoint.
+See also [code samples](https://github.com/openvinotoolkit/model_server/tree/v2022.3/client/python/kserve-api/samples) for running inference with KServe API on HTTP Inference endpoint.

src/example/SampleCpuExtension/README.md

@@ -8,7 +8,7 @@ custom extension execution.
 
 ## Creating cpu_extension library
 
-Compile the library by running `make cpu_extension BASE_OS=ubuntu` in root directory of [Model Server repository](https://github.com/openvinotoolkit/model_server/tree/develop). The implementation of this library slightly differs from the template in OpenVINO™ repository and can be found in [SampleCpuExtension directory](https://github.com/openvinotoolkit/model_server/tree/develop/src/example/SampleCpuExtension).
+Compile the library by running `make cpu_extension BASE_OS=ubuntu` in root directory of [Model Server repository](https://github.com/openvinotoolkit/model_server/tree/v2022.3). The implementation of this library slightly differs from the template in OpenVINO™ repository and can be found in [SampleCpuExtension directory](https://github.com/openvinotoolkit/model_server/tree/v2022.3/src/example/SampleCpuExtension).
 
 Shared library will be generated in the `lib` folder. Such library can be used to run Model Server, using `--cpu_extension` argument.