jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

doc: fix CodeGen/README.md markdown (#475)

Browse Source 
* fix multiple H1 headings
* edit use of please
* remove use of unnecessary HTML tags

Signed-off-by: David B. Kinder <david.b.kinder@intel.com>
Co-authored-by: Abolfazl Shahbazi <abolfazl.shahbazi@intel.com>
This commit is contained in:
David Kinder
2024-07-30 18:24:12 -07:00
committed by GitHub
parent 076bca3bbf
commit 33f83293d6
1 changed files with 48 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
CodeGen/README.md
View File

@@ -18,7 +18,7 @@ The workflow falls into the following architecture:
![architecture](./assets/img/codegen_architecture.png) ![architecture](./assets/img/codegen_architecture.png)
# Deploy CodeGen Service ## Deploy CodeGen Service
The CodeGen service can be effortlessly deployed on either Intel Gaudi2 or Intel Xeon Scalable Processor. The CodeGen service can be effortlessly deployed on either Intel Gaudi2 or Intel Xeon Scalable Processor.
@@ -26,57 +26,57 @@ Currently we support two ways of deploying ChatQnA services with docker compose:
1. Start services using the docker image on `docker hub`: 1. Start services using the docker image on `docker hub`:
```bash ```bash
docker pull opea/codegen:latest docker pull opea/codegen:latest
``` ```
2. Start services using the docker images `built from source`: [Guide](./docker) 2. Start services using the docker images `built from source`: [Guide](./docker)
## Setup Environment Variable ### Setup Environment Variable
To set up environment variables for deploying ChatQnA services, follow these steps: To set up environment variables for deploying ChatQnA services, follow these steps:
1. Set the required environment variables: 1. Set the required environment variables:
```bash ```bash
# Example: host_ip="192.168.1.1" # Example: host_ip="192.168.1.1"
export host_ip="External_Public_IP" export host_ip="External_Public_IP"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1" # Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy" export no_proxy="Your_No_Proxy"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token" export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
``` ```
2. If you are in a proxy environment, also set the proxy-related environment variables: 2. If you are in a proxy environment, also set the proxy-related environment variables:
```bash ```bash
export http_proxy="Your_HTTP_Proxy" export http_proxy="Your_HTTP_Proxy"
export https_proxy="Your_HTTPs_Proxy" export https_proxy="Your_HTTPs_Proxy"
``` ```
3. Set up other environment variables: 3. Set up other environment variables:
```bash ```bash
source ./docker/set_env.sh source ./docker/set_env.sh
``` ```
## Deploy CodeGen using Docker ### Deploy CodeGen using Docker
### Deploy CodeGen on Gaudi #### Deploy CodeGen on Gaudi
Please find corresponding [compose.yaml](./docker/gaudi/compose.yaml). Find the corresponding [compose.yaml](./docker/gaudi/compose.yaml).
```bash ```bash
cd GenAIExamples/CodeGen/docker/gaudi cd GenAIExamples/CodeGen/docker/gaudi
docker compose up -d docker compose up -d
``` ```
> Notice: Currently only the <b>Habana Driver 1.16.x</b> is supported for Gaudi. > Notice: Currently only the **Habana Driver 1.16.xi** is supported for Gaudi.
Please refer to the [Gaudi Guide](./docker/gaudi/README.md) to build docker images from source. Refer to the [Gaudi Guide](./docker/gaudi/README.md) to build docker images from source.
### Deploy CodeGen on Xeon #### Deploy CodeGen on Xeon
Please find corresponding [compose.yaml](./docker/xeon/compose.yaml). Find the corresponding [compose.yaml](./docker/xeon/compose.yaml).
```bash ```bash
cd GenAIExamples/CodeGen/docker/xeon cd GenAIExamples/CodeGen/docker/xeon
@@ -85,46 +85,46 @@ docker compose up -d
Refer to the [Xeon Guide](./docker/xeon/README.md) for more instructions on building docker images from source. Refer to the [Xeon Guide](./docker/xeon/README.md) for more instructions on building docker images from source.
## Deploy CodeGen using Kubernetes ### Deploy CodeGen using Kubernetes
Refer to the [Kubernetes Guide](./kubernetes/manifests/README.md) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi. Refer to the [Kubernetes Guide](./kubernetes/manifests/README.md) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi.
## Deploy CodeGen into Kubernetes using Helm Chart ### Deploy CodeGen into Kubernetes using Helm Chart
Install Helm (version >= 3.15) first. Please refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information. Install Helm (version >= 3.15) first. Refer to the [Helm Installation Guide](https://helm.sh/docs/intro/install/) for more information.
Refer to the [CodeGen helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codegen) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi. Refer to the [CodeGen helm chart](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts/codegen) for instructions on deploying CodeGen into Kubernetes on Xeon & Gaudi.
# Consume CodeGen Service ## Consume CodeGen Service
Two ways of consuming CodeGen Service: Two ways of consuming CodeGen Service:
1. Use cURL command on terminal 1. Use cURL command on terminal
```bash ```bash
curl http://${host_ip}:7778/v1/codegen \ curl http://${host_ip}:7778/v1/codegen \
-H "Content-Type: application/json" \ -H "Content-Type: application/json" \
-d '{"messages": "Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception."}' -d '{"messages": "Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception."}'
``` ```
2. Access via frontend 2. Access via frontend
To access the frontend, open the following URL in your browser: http://{host_ip}:5173. To access the frontend, open the following URL in your browser: http://{host_ip}:5173.
By default, the UI runs on port 5173 internally. By default, the UI runs on port 5173 internally.
# Troubleshooting ## Troubleshooting
1. If you get errors like "Access Denied", please [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/CodeGen/docker/xeon#validate-microservices) first. A simple example: 1. If you get errors like "Access Denied", [validate micro service](https://github.com/opea-project/GenAIExamples/tree/main/CodeGen/docker/xeon#validate-microservices) first. A simple example:
```bash ```bash
http_proxy="" http_proxy=""
curl http://${host_ip}:8028/generate \ curl http://${host_ip}:8028/generate \
-X POST \ -X POST \
-d '{"inputs":"Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception.","parameters":{"max_new_tokens":256, "do_sample": true}}' \ -d '{"inputs":"Implement a high-level API for a TODO list application. The API takes as input an operation request and updates the TODO list in place. If the request is invalid, raise an exception.","parameters":{"max_new_tokens":256, "do_sample": true}}' \
-H 'Content-Type: application/json' -H 'Content-Type: application/json'
``` ```
2. (Docker only) If all microservices work well, please check the port ${host_ip}:7778, the port may be allocated by other users, you can modify the `compose.yaml`. 2. (Docker only) If all microservices work well, check the port ${host_ip}:7778, the port may be allocated by other users, you can modify the `compose.yaml`.
3. (Docker only) If you get errors like "The container name is in use", please change container name in `compose.yaml`. 3. (Docker only) If you get errors like "The container name is in use", change container name in `compose.yaml`.