(docs) proxy

docs/my-website/docs/proxy/caching.md

@@ -1,4 +1,6 @@
 # Caching 
+Cache LLM Responses
+
 Caching can be enabled by adding the `cache` key in the `config.yaml`
 #### Step 1: Add `cache` to the config.yaml
 ```yaml

docs/my-website/docs/proxy/cli.md

@@ -1,4 +1,5 @@
 # CLI Arguments
+Cli arguments,  --host, --port, --num_workers
 
 #### --host
    - **Default:** `'0.0.0.0'`

docs/my-website/docs/proxy/configs.md

@@ -1,5 +1,5 @@
-# Config.yaml
-The Config allows you to set the following params
+# Proxy Config.yaml
+Set model list, `api_base`, `api_key`, `temperature` & proxy server settings (`maaster-key`)
 
 | Param Name           | Description                                                   |
 |----------------------|---------------------------------------------------------------|

docs/my-website/docs/proxy/load_balancing.md

@@ -1,6 +1,8 @@
 
 # Load Balancing - Multiple Instances of 1 model
-Use this config to load balance between multiple instances of the same model. The proxy will handle routing requests (using LiteLLM's Router). **Set `rpm` in the config if you want maximize throughput**
+Load balance multiple instances of the same model
+
+The proxy will handle routing requests (using LiteLLM's Router). **Set `rpm` in the config if you want maximize throughput**
 
 #### Example config
 requests with `model=gpt-3.5-turbo` will be routed across multiple instances of `azure/gpt-3.5-turbo`

docs/my-website/docs/proxy/logging.md

@@ -1,4 +1,5 @@
 # Logging - OpenTelemetry, Langfuse, ElasticSearch 
+Log Proxy Input, Output, Exceptions to Langfuse, OpenTelemetry
 ## Logging Proxy Input/Output - OpenTelemetry
 
 ### Step 1 Start OpenTelemetry Collecter Docker Container

docs/my-website/docs/proxy/virtual_keys.md

@@ -1,5 +1,6 @@
 
 # Cost Tracking & Virtual Keys
+Track Spend and create virtual keys for the proxy
 
 Grant other's temporary access to your proxy, with keys that expire after a set duration.