From c548d8ad372cea8883c04c8ae19974e7f865f312 Mon Sep 17 00:00:00 2001
From: ishaan-jaff <ishaanjaffer0324@gmail.com>
Date: Sat, 9 Sep 2023 16:11:11 -0700
Subject: [PATCH] update docs

---
 .../docs/providers/custom_openai_proxy.md     | 44 +++++++++++++++++++
 docs/my-website/docs/providers/vllm.md        |  4 +-
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/docs/my-website/docs/providers/custom_openai_proxy.md b/docs/my-website/docs/providers/custom_openai_proxy.md
index e69de29bb2..8b661fddf7 100644
--- a/docs/my-website/docs/providers/custom_openai_proxy.md
+++ b/docs/my-website/docs/providers/custom_openai_proxy.md
@@ -0,0 +1,44 @@
+# OpenAI Proxy Servers (ChatCompletion)
+
+LiteLLM allows you to call your OpenAI ChatCompletion proxy server
+
+
+### API KEYS
+No api keys required
+
+### Example Usage
+
+#### Pre-Requisites
+Ensure your proxy server has the following route
+
+```python
+@app.route('/chat/completions', methods=["POST"])
+def chat_completion():
+  print("got request for chat completion")
+
+```
+
+In order to use your custom OpenAI Chat Completion proxy with LiteLLM, ensure you set
+
+* `api_base` to your proxy url, example "https://openai-proxy.berriai.repl.co"
+* `custom_llm_provider` to `openai` this ensures litellm uses the `openai.ChatCompletion` to your api_base
+
+```python
+
+from litellm import completion
+
+## set ENV variables
+os.environ["OPENAI_API_KEY"] = "set it, but it's not used"
+
+messages = [{ "content": "Hello, how are you?","role": "user"}]
+
+response = completion(
+    model="command-nightly", 
+    messages=[{ "content": "Hello, how are you?","role": "user"}],
+    api_base="https://openai-proxy.berriai.repl.co",
+    custom_llm_provider="openai"
+    temperature=0.2,
+    max_tokens=80,
+)
+print(response)
+```
\ No newline at end of file
diff --git a/docs/my-website/docs/providers/vllm.md b/docs/my-website/docs/providers/vllm.md
index 1b1e18add2..d97f09eaef 100644
--- a/docs/my-website/docs/providers/vllm.md
+++ b/docs/my-website/docs/providers/vllm.md
@@ -24,7 +24,7 @@ print(response)
 In order to use litellm to call a hosted vllm server add the following to your completion call
 
 * `custom_llm_provider == "openai"`
-* `api_base = "your-hosted-vllm-server/v1"`
+* `api_base = "your-hosted-vllm-server"`
 
 ```python
 import litellm 
@@ -32,7 +32,7 @@ import litellm
 response = completion(
             model="facebook/opt-125m", # pass the vllm model name
             messages=messages,
-            api_base="https://hosted-vllm-api.co/v1",
+            api_base="https://hosted-vllm-api.co",
             custom_llm_provider="openai",
             temperature=0.2,
             max_tokens=80)