From f3c00a0e372c8479b482570c2486b1b015df0658 Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Sat, 21 Oct 2023 18:28:30 -0700
Subject: [PATCH] docs(openai-proxy-docs): cleanupo

---
 openai-proxy/README.md | 56 ++++++++++++++++++++----------------------
 1 file changed, 27 insertions(+), 29 deletions(-)

diff --git a/openai-proxy/README.md b/openai-proxy/README.md
index 413c55b2c8..d1c1def76f 100644
--- a/openai-proxy/README.md
+++ b/openai-proxy/README.md
@@ -1,47 +1,45 @@
-# litellm-proxy
+# openai-proxy
 
-A local, fast, and lightweight **OpenAI-compatible server** to call 100+ LLM APIs.
+A simple, fast, and lightweight **OpenAI-compatible server** to call 100+ LLM APIs.
 
 ## usage 
 
 ```shell 
-$ pip install litellm
+$ git clone https://github.com/BerriAI/litellm.git
 ```
 ```shell
-$ litellm --model ollama/codellama 
+$ cd ./litellm/openai-proxy
+```
 
-#INFO: Ollama running on http://0.0.0.0:8000
+```shell
+$ uvicorn main:app --host 0.0.0.0 --port 8000
 ```
 
 ## replace openai base
 ```python 
 import openai 
-
 openai.api_base = "http://0.0.0.0:8000"
 
-print(openai.ChatCompletion.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
+# call cohere
+openai.api_key = "my-cohere-key" # this gets passed as a header 
+
+response = openai.ChatCompletion.create(model="command-nightly", messages=[{"role":"user", "content":"Hey!"}])
+
+# call bedrock 
+response = openai.ChatCompletion.create(
+    model = "bedrock/anthropic.claude-instant-v1",
+    messages = [
+        {
+            "role": "user",
+            "content": "Hey!"
+        }
+    ],
+    aws_access_key_id="",
+    aws_secret_access_key="",
+    aws_region_name="us-west-2",
+)
+
+print(response)
 ``` 
 
 [**See how to call Huggingface,Bedrock,TogetherAI,Anthropic, etc.**](https://docs.litellm.ai/docs/proxy_server)
-
-## configure proxy
-
-To save API Keys, change model prompt, etc. you'll need to create a local instance of it:
-```shell
-$ litellm --create-proxy
-```
-This will create a local project called `litellm-proxy` in your current directory, that has: 
-* **proxy_cli.py**: Runs the proxy
-* **proxy_server.py**: Contains the API calling logic
-    - `/chat/completions`: receives `openai.ChatCompletion.create` call.
-    - `/completions`: receives `openai.Completion.create` call.
-    - `/models`: receives `openai.Model.list()` call
-* **secrets.toml**: Stores your api keys, model configs, etc.
-
-Run it by doing:
-```shell
-$ cd litellm-proxy
-```
-```shell
-$ python proxy_cli.py --model ollama/llama # replace with your model name
-```
\ No newline at end of file