updated the on-prem guide

on_prem/universal_api.mdx

@@ -2,65 +2,83 @@
 title: 'Universal API'
 ---
 
-Below are the steps to use the universal API in an on-prem manner.
-
-1. Once access is granted, run `docker pull unifyai/sso:latest`
-
-2. Then run `docker run -dt -p 8000:8000 –env-file <env_file_path> unifyai/sso:latest`
-
-3. The env file should look like this.
-
-```bash
-DEEPINFRA_API_KEY=
-STABILITY_API_KEY=
-MISTRAL_AI_API_KEY=
-PERPLEXITY_AI_API_KEY=
-ANYSCALE_API_KEY=
-OCTOAI_API_KEY=
-OPENAI_API_KEY=
-TOGETHER_AI_API_KEY=
-REPLICATE_API_KEY=
-LEPTON_AI_API_KEY=
-FIREWORKS_AI_API_KEY=
-ANTHROPIC_API_KEY=
-###
-VERTEXAI_SERVICE_ACC_JSON=
-VERTEXAI_GCLOUD_PATH=
-VERTEXAI_PROJECT=
-VERTEXAI_LOCATION=
-```
-
-4. Now you have your sso service running locally which you can use like this.
-    - Using python + requests
-    ```python
-    import requests
-    messages = [{"role": "user", "content": "What's the weather like in San Francisco, Tokyo, and Paris?"}]
-
-    res = requests.post("http://localhost:8000/chat/completions", json={
-        "model": "claude-3-haiku@anthropic",
-        "messages": messages,
-    },).json()
-    ```
-
-    - Using our python client
-    ```python
-    from unify import Unify
-    api = Unify("claude-3-haiku@anthropic", api_key=<RANDOM_KEY_WONT_BE_USED>)
-    api.client.base_url = “http://localhost:8000”
-    api.generate("What is the meaning of life?")
-    ```
-
-    - Using curl
-    ```bash
-    curl -X 'POST' \
-    'http://localhost:8000/chat/completions' \
-    -H 'accept: application/json' \
-    -H 'Content-Type: application/json' \
-    -d '{
-    "model": "claude-3-haiku@anthropic",
-        "messages": [{
-            "role": "user",
-            "content": "Explain who Newton was and his entire theory of gravitation. Give a long detailed response please and explain all of his achievements"
-        }],
-    }'
-    ```
+## Sign up to the platform
+
+Even though you would have your own on-prem console, you would need to sign in through the
+[public](https://console.unify.ai/) one so that you have a user id and an api key.
+
+## Get access to the docker images
+
+We have pushed the images you’d need to set up with on docker hub. Given that the images are private,
+you would need to provide us with the docker user to which you would want the images shared.
+You would then use that account to pull those images for setting up.
+
+## Pull the images
+
+In order to set up on-prem, you would need to pull 3 images,
+- **unify/orchestra-on-prem:latest**: The backend app
+- **unify/dataset_evaluation-on-prem:latest**: The dataset evaluation service
+- **unify/unify-interfaces-on-prem:latest**: The console app
+Given that these images are private, you would need to [log in](https://docs.docker.com/reference/cli/docker/login/)
+to docker before pulling the images.
+
+## Local folder structure
+
+We have shared a folder with you which contains the necessary configs to set up.
+This section is mainly for explaning what’s contained in the folder, you don’t need to edit anything manually
+(except VertexAI users as explained in the next section). Following are the folder contents,
+- `shared_volume`: A folder that would be shared between the images and would contain the information about
+various dataset evaluations you’ve run (in the uploaded_datasets folder) and the custom endpoints and api keys
+you’re using (in the db folder)
+- `.env_orchestra`: Contains the necessary environment variables to set up the backend app
+- `.env_console`: Contains the necessary environment variables to set up the console app
+- `sessionInfo.json`: The session information for the console app, it’s mainly used for displaying data on your
+profile page. The file should contain the following fields when we share the folder with you,
+    - `name`: first name
+    - `email`: email id
+    - `image`: a link to the profile image
+    - `userInfo.json`: Contains more information about the user currently using the app.
+    This is something we need to do so to bypass the login process. The file should contain the following
+    fields when we share the folder with you,
+        - `id`: user id
+        - `name`: first name
+        - `lastName`: last name
+        - `image`: a link to the profile image
+        - `email`: the email id
+        - `createdAt`: the date when the account was created
+        - `apiKey`: the details about your api key
+        - `UserDetails`: your organization and jobTitle (Optional)
+        - `docker-compose.yaml`: The compose file to get the containers set up
+
+## Setting up
+
+In order to set up, you would need to populate the `.env_orchestra` file with the credentials of the providers
+you would like to use,
+- For providers like OpenAI, Anthropic, etc. (which require a single API key), you would need to add your key
+corresponding to the `ORCHESTRA_OPENAI_KEY` variable and so on.
+- For using AWS Bedrock, you would need to add,
+    - `AWS_SECRET_KEY_ID`
+    - `AWS_SECRET_ACCESS_KEY`
+    - `AWS_REGION`
+- For using VertexAI, you would need to add,
+    - `GOOGLE_APPLICATION_CREDENTIALS`
+    - `ORCHESTRA_VERTEXAI_PROJECT`
+    - `ORCHESTRA_VERTEXAI_LOCATION`
+
+Along with the above, you would also need to uncomment a line in the docker-compose.yaml that mounts the service
+account json onto the container. For e.g. if `application_default_credentials.json` is the name of the file, then
+`GOOGLE_APPLICATION_CREDENTIALS` would be set as `/app/src/application_default_credentials.json`.
+
+Once you’ve set the environment variables, you can now spin up the containers for the images with docker compose up.
+
+The containers should start running after that, you should wait until you see the log entry of on-prem-orchestra
+saying Uvicorn running on `http://0.0.0.0:8000`. After that is displayed, you’re set to start using the console.
+
+## Usage
+
+The console should be usable at `http://localhost:3000`, you should be able to access features like uploading datasets
+and running evaluations, adding custom api keys and endpoints and so on. You can also use all the endpoints in the
+API Reference by making calls to `http://localhost:8000` instead of `https://api.unify.ai`
+
+The shared_volume would contain the results of the dataset evaluations and custom endpoints you create. You shouldn’t
+need to update this folder manually, the information stored in it can be retrieved from the relevant endpoints.