From cdae08f3c30aeb83bff76bbe80c4584a325dbef5 Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Mon, 1 Apr 2024 12:09:08 -0700
Subject: [PATCH] docs(openai.md): fix docs to include example of calling
 openai on proxy

---
 docs/my-website/docs/providers/openai.md | 110 +++++++++++++++++++++++
 litellm/proxy/_new_secret_config.yaml    |  23 +++--
 2 files changed, 124 insertions(+), 9 deletions(-)

diff --git a/docs/my-website/docs/providers/openai.md b/docs/my-website/docs/providers/openai.md
index aa42847b1..c50cc7598 100644
--- a/docs/my-website/docs/providers/openai.md
+++ b/docs/my-website/docs/providers/openai.md
@@ -1,3 +1,6 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
 # OpenAI
 LiteLLM supports OpenAI Chat + Text completion and embedding calls.
 
@@ -22,6 +25,113 @@ response = completion(
 )
 ```
 
+### Proxy Usage
+
+Here's how to call OpenAI models with the LiteLLM Proxy Server
+
+### 1. Save key in your environment
+
+```bash
+export OPENAI_API_KEY=""
+```
+
+### 2. Start the proxy 
+
+<Tabs>
+<TabItem value="cli" label="CLI">
+
+```bash
+$ litellm --model gpt-3.5-turbo
+
+# Server running on http://0.0.0.0:4000
+```
+</TabItem>
+<TabItem value="config" label="config.yaml">
+
+```yaml
+model_list:
+  - model_name: gpt-3.5-turbo
+    litellm_params:
+      model: gpt-3.5-turbo
+```
+</TabItem>
+</Tabs>
+
+### 3. Test it
+
+
+<Tabs>
+<TabItem value="Curl" label="Curl Request">
+
+```shell
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--data ' {
+      "model": "gpt-3.5-turbo",
+      "messages": [
+        {
+          "role": "user",
+          "content": "what llm are you"
+        }
+      ]
+    }
+'
+```
+</TabItem>
+<TabItem value="openai" label="OpenAI v1.0.0+">
+
+```python
+import openai
+client = openai.OpenAI(
+    api_key="anything",
+    base_url="http://0.0.0.0:4000"
+)
+
+# request sent to model set on litellm proxy, `litellm --model`
+response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
+    {
+        "role": "user",
+        "content": "this is a test request, write a short poem"
+    }
+])
+
+print(response)
+
+```
+</TabItem>
+<TabItem value="langchain" label="Langchain">
+
+```python
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    HumanMessagePromptTemplate,
+    SystemMessagePromptTemplate,
+)
+from langchain.schema import HumanMessage, SystemMessage
+
+chat = ChatOpenAI(
+    openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
+    model = "gpt-3.5-turbo",
+    temperature=0.1
+)
+
+messages = [
+    SystemMessage(
+        content="You are a helpful assistant that im using to make a test request to."
+    ),
+    HumanMessage(
+        content="test from litellm. tell me why it's amazing in 1 sentence"
+    ),
+]
+response = chat(messages)
+
+print(response)
+```
+</TabItem>
+</Tabs>
+
+
 ### Optional Keys - OpenAI Organization, OpenAI API Base
 
 ```python
diff --git a/litellm/proxy/_new_secret_config.yaml b/litellm/proxy/_new_secret_config.yaml
index dde07bb87..003597eaa 100644
--- a/litellm/proxy/_new_secret_config.yaml
+++ b/litellm/proxy/_new_secret_config.yaml
@@ -4,18 +4,23 @@ model_list:
     model: openai/my-fake-model
     api_key: my-fake-key
     api_base: https://exampleopenaiendpoint-production.up.railway.app/
+- model_name: gpt-instruct
+  litellm_params:
+    model: gpt-3.5-turbo-instruct
+    # api_key: my-fake-key
+    # api_base: https://exampleopenaiendpoint-production.up.railway.app/
 
-litellm_settings:
-  cache: true
+# litellm_settings:
+#   cache: true
 #   max_budget: 600020
 #   budget_duration: 30d
 
 general_settings:
   master_key: sk-1234
-  proxy_batch_write_at: 60 # 👈 Frequency of batch writing logs to server (in seconds)
-  enable_jwt_auth: True
-  alerting: ["slack"]
-  litellm_jwtauth:
-    admin_jwt_scope: "litellm_proxy_admin"
-    team_jwt_scope: "litellm_team" 
-    public_key_ttl: 600
\ No newline at end of file
+  # proxy_batch_write_at: 60 # 👈 Frequency of batch writing logs to server (in seconds)
+  # enable_jwt_auth: True
+  # alerting: ["slack"]
+  # litellm_jwtauth:
+  #   admin_jwt_scope: "litellm_proxy_admin"
+  #   team_jwt_scope: "litellm_team" 
+  #   public_key_ttl: 600
\ No newline at end of file