From ad7dfd2edbe5e9b30fbff06b0913e1003654bd68 Mon Sep 17 00:00:00 2001
From: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Date: Thu, 19 Dec 2024 18:51:55 -0800
Subject: [PATCH] docs infinity rerank api docs

---
 docs/my-website/docs/providers/infinity.md | 67 ++++++++++++++++++++++
 docs/my-website/docs/rerank.md             |  3 +-
 docs/my-website/sidebars.js                |  1 +
 3 files changed, 70 insertions(+), 1 deletion(-)
 create mode 100644 docs/my-website/docs/providers/infinity.md

diff --git a/docs/my-website/docs/providers/infinity.md b/docs/my-website/docs/providers/infinity.md
new file mode 100644
index 0000000000..dd6986dfef
--- /dev/null
+++ b/docs/my-website/docs/providers/infinity.md
@@ -0,0 +1,67 @@
+# Infinity
+
+| Property | Details |
+|-------|-------|
+| Description | Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip|
+| Provider Route on LiteLLM | `infinity/` |
+| Supported Operations | `/rerank` |
+| Link to Provider Doc | [Infinity ↗](https://github.com/michaelfeil/infinity) |
+
+
+## **Usage - LiteLLM Python SDK**
+
+```python
+from litellm import rerank
+
+response = rerank(
+    model="infinity/rerank",
+    query="What is the capital of France?",
+    documents=["Paris", "London", "Berlin", "Madrid"],
+)
+```
+
+## **Usage - LiteLLM Proxy**
+
+LiteLLM provides an cohere api compatible `/rerank` endpoint for Rerank calls.
+
+**Setup**
+
+Add this to your litellm proxy config.yaml
+
+```yaml
+model_list:
+  - model_name: custom-infinity-rerank
+    litellm_params:
+      model: infinity/rerank
+      api_key: os.environ/INFINITY_API_KEY
+      api_base: https://localhost:8080
+```
+
+Start litellm
+
+```bash
+litellm --config /path/to/config.yaml
+
+# RUNNING on http://0.0.0.0:4000
+```
+
+Test request
+
+```bash
+curl http://0.0.0.0:4000/rerank \
+  -H "Authorization: Bearer sk-1234" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "custom-infinity-rerank",
+    "query": "What is the capital of the United States?",
+    "documents": [
+        "Carson City is the capital city of the American state of Nevada.",
+        "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
+        "Washington, D.C. is the capital of the United States.",
+        "Capital punishment has existed in the United States since before it was a country."
+    ],
+    "top_n": 3
+  }'
+```
+
+
diff --git a/docs/my-website/docs/rerank.md b/docs/my-website/docs/rerank.md
index b630a8cd8d..598c672942 100644
--- a/docs/my-website/docs/rerank.md
+++ b/docs/my-website/docs/rerank.md
@@ -115,4 +115,5 @@ curl http://0.0.0.0:4000/rerank \
 | Together AI|   [Usage](../docs/providers/togetherai)                 |  
 | Azure AI|   [Usage](../docs/providers/azure_ai)                 |  
 | Jina AI|   [Usage](../docs/providers/jina_ai)                 |  
-| AWS Bedrock|   [Usage](../docs/providers/bedrock#rerank-api)                 |  
\ No newline at end of file
+| AWS Bedrock|   [Usage](../docs/providers/bedrock#rerank-api)                 |  
+| Infinity|   [Usage](../docs/providers/infinity)                 |  
\ No newline at end of file
diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js
index 931b0ecebe..90256deabf 100644
--- a/docs/my-website/sidebars.js
+++ b/docs/my-website/sidebars.js
@@ -186,6 +186,7 @@ const sidebars = {
         "providers/fireworks_ai",
         "providers/clarifai", 
         "providers/vllm", 
+        "providers/infinity",
         "providers/xinference", 
         "providers/cloudflare_workers", 
         "providers/deepinfra",