You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* fix multiple H1 headings
* indent content of ordered list
* edit use of please
* edit unnecessary use of HTML
Signed-off-by: David B. Kinder <[email protected]>
Co-authored-by: Abolfazl Shahbazi <[email protected]>
This Code Translation use case uses Text Generation Inference on Intel Gaudi2 or Intel Xeon Scalable Processor. The Intel Gaudi2 accelerator supports both training and inference for deep learning models in particular for LLMs. Please visit[Habana AI products](https://habana.ai/products) for more details.
9
+
This Code Translation use case uses Text Generation Inference on Intel Gaudi2 or Intel Xeon Scalable Processor. The Intel Gaudi2 accelerator supports both training and inference for deep learning models in particular for LLMs. Visit[Habana AI products](https://habana.ai/products) for more details.
10
10
11
-
# Deploy Code Translation Service
11
+
##Deploy Code Translation Service
12
12
13
13
The Code Translation service can be effortlessly deployed on either Intel Gaudi2 or Intel Xeon Scalable Processor.
14
14
15
15
Currently we support two ways of deploying Code Translation services on docker:
16
16
17
17
1. Start services using the docker image on `docker hub`:
18
18
19
-
```bash
20
-
docker pull opea/codetrans:latest
21
-
```
19
+
```bash
20
+
docker pull opea/codetrans:latest
21
+
```
22
22
23
23
2. Start services using the docker images `built from source`: [Guide](./docker)
24
24
25
-
## Setup Environment Variable
25
+
###Setup Environment Variable
26
26
27
27
To set up environment variables for deploying Code Translation services, follow these steps:
Find the corresponding [compose.yaml](./docker/xeon/compose.yaml).
70
70
71
71
```bash
72
72
cd GenAIExamples/CodeTrans/docker/xeon
@@ -75,50 +75,50 @@ docker compose up -d
75
75
76
76
Refer to the [Xeon Guide](./docker/xeon/README.md) for more instructions on building docker images from source.
77
77
78
-
## Deploy using Kubernetes with GMC
78
+
###Deploy using Kubernetes with GMC
79
79
80
-
Please refer to the [Code Translation Kubernetes Guide](./kubernetes/README.md)
80
+
Refer to the [Code Translation Kubernetes Guide](./kubernetes/README.md)
81
81
82
-
## Deploy using Kubernetes without GMC
82
+
###Deploy using Kubernetes without GMC
83
83
84
-
Please refer to the [Code Translation Kubernetes Guide](./kubernetes/manifests/README.md)
84
+
Refer to the [Code Translation Kubernetes Guide](./kubernetes/manifests/README.md)
85
85
86
-
## Deploy CodeTrans into Kubernetes using Helm Chart
86
+
###Deploy CodeTrans into Kubernetes using Helm Chart
87
87
88
-
Install Helm (version >= 3.15) first. Please refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
88
+
Install Helm (version >= 3.15) first. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
89
89
90
90
Refer to the [CodeTrans helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codetrans) for instructions on deploying CodeTrans into Kubernetes on Xeon & Gaudi.
To access the frontend, open the following URL in your browser: http://{host_ip}:5173.
107
107
108
108
By default, the UI runs on port 5173 internally.
109
109
110
-
# Troubleshooting
110
+
##Troubleshooting
111
111
112
-
1. If you get errors like "Access Denied", please [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/CodeTrans/docker/xeon#validate-microservices) first. A simple example:
112
+
1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/CodeTrans/docker/xeon#validate-microservices) first. A simple example:
113
113
114
-
```bash
115
-
http_proxy=""
116
-
curl http://${host_ip}:8008/generate \
117
-
-X POST \
118
-
-d '{"inputs":" ### System: Please translate the following Golang codes into Python codes. ### Original codes: '\'''\'''\''Golang \npackage main\n\nimport \"fmt\"\nfunc main() {\n fmt.Println(\"Hello, World!\");\n '\'''\'''\'' ### Translated codes:","parameters":{"max_new_tokens":17, "do_sample": true}}' \
119
-
-H 'Content-Type: application/json'
120
-
```
114
+
```bash
115
+
http_proxy=""
116
+
curl http://${host_ip}:8008/generate \
117
+
-X POST \
118
+
-d '{"inputs":" ### System: Please translate the following Golang codes into Python codes. ### Original codes: '\'''\'''\''Golang \npackage main\n\nimport \"fmt\"\nfunc main() {\n fmt.Println(\"Hello, World!\");\n '\'''\'''\'' ### Translated codes:","parameters":{"max_new_tokens":17, "do_sample": true}}' \
119
+
-H 'Content-Type: application/json'
120
+
```
121
121
122
-
2. (Docker only) If all microservices work well, please check the port ${host_ip}:7777, the port may be allocated by other users, you can modify the `compose.yaml`.
122
+
2. (Docker only) If all microservices work well, check the port ${host_ip}:7777, the port may be allocated by other users, you can modify the `compose.yaml`.
123
123
124
-
3. (Docker only) If you get errors like "The container name is in use", please change container name in `compose.yaml`.
124
+
3. (Docker only) If you get errors like "The container name is in use", change container name in `compose.yaml`.
0 commit comments