Update deploy-openai-llm-byoc.md

Author: mayoor

LLM/deploy-openai-llm-byoc.md

@@ -1,6 +1,7 @@
 # Deploy OpenAI open-source models
 
-This guide demonstrates how to deploy and perform inference using AI Quick Action registered models with Oracle Data Science Service Managed Containers (SMC) powered by vLLM. In this example, we will use a model downloaded from Hugging Face specifically, [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) from OpenAI. 
+This guide demonstrates how to deploy and perform inference using OCI Data Science Service. In this example, we will use a model downloaded from Hugging Face specifically, [openai/gpt-oss-120b](https://huggingface.co/openai/gpt-oss-120b) from OpenAI. 
+
 
 
 ## Required IAM Policies
@@ -9,40 +10,58 @@ Add these [policies](https://github.com/oracle-samples/oci-data-science-ai-sampl
 
 ## Setup
 
+Create a data science notebook session with at least 400GB of space. We will use notebook session to - 
+1. Download model weights
+2. Create Model Catalog entry
+3. Deploy the model
 
+To prepare inference container, we will use local laptop since this step requires docker commmands. The notebook session does not come with the docker tooling.
 
-```shell
-# Install required python packages
 
-pip install oracle-ads
-pip install oci
-pip install huggingface_hub
-```
+# Prepare Inference container
 
+vLLM is an easy-to-use library for LLM inference and server.  You can get the container image from [DockerHub](https://hub.docker.com/r/vllm/vllm-openai/tags).
+
+Following commands are to run on your laptop - 
+
+```shell
+docker pull --platform linux/amd64 vllm/vllm-openai:gptoss
+```
 
+Currently, OCI Data Science Model Deployment only supports container images residing in the OCI Registry.  Before we can push the pulled vLLM container, make sure you have created a repository in your tenancy.  
+- Go to your tenancy Container Registry
+- Click on the Create repository button
+- Select Private under Access types
+- Set a name for Repository name.  We are using "vllm-odsc "in the example.
+- Click on Create button
 
-### Common variables
+You may need to docker login to the Oracle Cloud Container Registry (OCIR) first, if you haven't done so before in order to push the image. To login, you have to use your API Auth Token that can be created under your Oracle Cloud Account->Auth Token. You need to login only once. Replace <region> with the OCI region you are using.
 
+```shell
+docker login -u '<tenant-namespace>/<username>' <region>.ocir.io
+```
 
+If your tenancy is federated with Oracle Identity Cloud Service, use the format <tenancy-namespace>/oracleidentitycloudservice/<username>. You can then push the container image to the OCI Registry
 
-## API Endpoint Usage
+```shell
+docker tag vllm/vllm-openai:gptoss -t <region>.ocir.io/<tenancy>/vllm-odsc/vllm-openai:gptoss
+docker push <region>.ocir.io/<tenancy>/vllm-odsc/vllm-openai:gptoss
+```
 
-The `/v1/completions` is for interacting with non-chat base models or the instruction trained chat model. This endpoint provides the completion for a single prompt and takes a single string as input, whereas the `/v1/chat/completions` endpoint provides the responses for a given dialog and requires the input in a specific format corresponding to the message history. This guide uses `/v1/chat/completions` endpoint.
+# Deployment
 
+Following steps are to be performed on OCI Notebook Session - 
 
 ## Prepare The Model Artifacts
 
 To prepare Model artifacts for LLM model deployment:
 
-- Download the model files from huggingface to local directory using a valid huggingface token (only needed for gated models). If you don't have Huggingface Token, refer [this](https://huggingface.co/docs/hub/en/security-tokens) to generate one.
+- Download the model files from huggingface to local directory.
 - Upload the model folder to a [versioned bucket](https://docs.oracle.com/en-us/iaas/Content/Object/Tasks/usingversioning.htm) in Oracle Object Storage. If you don’t have an Object Storage bucket, create one using the OCI SDK or the Console. Create an Object Storage bucket. Make a note of the `namespace`, `compartment`, and `bucketname`. Configure the policies to allow the Data Science service to read and write the model artifact to the Object Storage bucket in your tenancy. An administrator must configure the policies in IAM in the Console.
 - Create model catalog entry for the model using the Object storage path
 
 ### Model Download from HuggingFace Model Hub
 
-
-
-
 [This documentation](https://huggingface.co/docs/huggingface_hub/en/guides/cli#download-an-entire-repository) provides more information on using `huggingface-cli` to download an entire repository at a given revision. Models in the HuggingFace hub are stored in their own repository.
 
 
@@ -120,33 +139,6 @@ model = (
 model.create(model_by_reference=True)
 ```
 
-## Inference container
-
-vLLM is an easy-to-use library for LLM inference and server.  You can get the container image from [DockerHub](https://hub.docker.com/r/vllm/vllm-openai/tags).
-
-```shell
-docker pull --platform linux/amd64 vllm/vllm-openai:gptoss
-```
-
-Currently, OCI Data Science Model Deployment only supports container images residing in the OCI Registry.  Before we can push the pulled vLLM container, make sure you have created a repository in your tenancy.  
-- Go to your tenancy Container Registry
-- Click on the Create repository button
-- Select Private under Access types
-- Set a name for Repository name.  We are using "vllm-odsc "in the example.
-- Click on Create button
-
-You may need to docker login to the Oracle Cloud Container Registry (OCIR) first, if you haven't done so before in order to push the image. To login, you have to use your API Auth Token that can be created under your Oracle Cloud Account->Auth Token. You need to login only once. Replace <region> with the OCI region you are using.
-
-```shell
-docker login -u '<tenant-namespace>/<username>' <region>.ocir.io
-```
-
-If your tenancy is federated with Oracle Identity Cloud Service, use the format <tenancy-namespace>/oracleidentitycloudservice/<username>. You can then push the container image to the OCI Registry
-
-```shell
-docker tag vllm/vllm-openai:gptoss -t <region>.ocir.io/<tenancy>/vllm-odsc/vllm-openai:gptoss
-docker push <region>.ocir.io/<tenancy>/vllm-odsc/vllm-openai:gptoss
-
 
 ### Import Model Deployment Modules
 
@@ -161,8 +153,6 @@ from ads.model.deployment import (
 
 ## Setup Model Deployment Infrastructure
 
-
-
 ```python
 container_image = "<region>.ocir.io/<tenancy>/vllm-odsc/vllm-openai:gptoss"  # name given to vllm image pushed to oracle  container registry
 ```