From 986c463983c8f48cf1b78fd4a51a1128beaa61ea Mon Sep 17 00:00:00 2001
From: Rashmi Pawar <168514198+raspawar@users.noreply.github.com>
Date: Tue, 28 Jan 2025 10:48:34 +0530
Subject: [PATCH] (doc) Add nvidia as provider (#8023)

* add nvidia as provider in docs

* fixes for closing tag

* review changes
---
 .../docs/embedding/supported_embedding.md     | 34 ++++++++++++++++++
 docs/my-website/docs/index.md                 | 36 +++++++++++++++++++
 docs/my-website/src/pages/index.md            | 36 +++++++++++++++++++
 3 files changed, 106 insertions(+)

diff --git a/docs/my-website/docs/embedding/supported_embedding.md b/docs/my-website/docs/embedding/supported_embedding.md
index 1f877ecc37..d0cb59b46e 100644
--- a/docs/my-website/docs/embedding/supported_embedding.md
+++ b/docs/my-website/docs/embedding/supported_embedding.md
@@ -323,6 +323,40 @@ response = embedding(
 | embed-english-light-v2.0 | `embedding(model="embed-english-light-v2.0", input=["good morning from litellm", "this is another item"])` |
 | embed-multilingual-v2.0  | `embedding(model="embed-multilingual-v2.0", input=["good morning from litellm", "this is another item"])` |
 
+## NVIDIA NIM Embedding Models
+
+### API keys
+This can be set as env variables or passed as **params to litellm.embedding()**
+```python
+import os
+os.environ["NVIDIA_NIM_API_KEY"] = ""  # api key
+os.environ["NVIDIA_NIM_API_BASE"] = "" # nim endpoint url
+```
+
+### Usage
+```python
+from litellm import embedding
+import os
+os.environ['NVIDIA_NIM_API_KEY'] = ""
+response = embedding(
+    model='nvidia_nim/<model_name>', 
+    input=["good morning from litellm"]
+)
+```
+All models listed [here](https://build.nvidia.com/explore/retrieval) are supported:
+
+| Model Name         | Function Call                                         |
+| :---               | :---                                                  |
+| NV-Embed-QA | `embedding(model="nvidia_nim/NV-Embed-QA", input)` |
+| nvidia/nv-embed-v1 | `embedding(model="nvidia_nim/nvidia/nv-embed-v1", input)` |
+| nvidia/nv-embedqa-mistral-7b-v2 | `embedding(model="nvidia_nim/nvidia/nv-embedqa-mistral-7b-v2", input)` |
+| nvidia/nv-embedqa-e5-v5 | `embedding(model="nvidia_nim/nvidia/nv-embedqa-e5-v5", input)` |
+| nvidia/embed-qa-4 | `embedding(model="nvidia_nim/nvidia/embed-qa-4", input)` |
+| nvidia/llama-3.2-nv-embedqa-1b-v1 | `embedding(model="nvidia_nim/nvidia/llama-3.2-nv-embedqa-1b-v1", input)` |
+| nvidia/llama-3.2-nv-embedqa-1b-v2 | `embedding(model="nvidia_nim/nvidia/llama-3.2-nv-embedqa-1b-v2", input)` |
+| snowflake/arctic-embed-l | `embedding(model="nvidia_nim/snowflake/arctic-embed-l", input)` |
+| baai/bge-m3 | `embedding(model="nvidia_nim/baai/bge-m3", input)` |
+
 ## HuggingFace Embedding Models
 LiteLLM supports all Feature-Extraction + Sentence Similarity Embedding models: https://huggingface.co/models?pipeline_tag=feature-extraction
 
diff --git a/docs/my-website/docs/index.md b/docs/my-website/docs/index.md
index 0f5c8b84a5..dd845576c7 100644
--- a/docs/my-website/docs/index.md
+++ b/docs/my-website/docs/index.md
@@ -108,6 +108,24 @@ response = completion(
 
 </TabItem>
 
+<TabItem value="nvidia" label="NVIDIA">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables
+os.environ["NVIDIA_NIM_API_KEY"] = "nvidia_api_key"
+os.environ["NVIDIA_NIM_API_BASE"] = "nvidia_nim_endpoint_url"
+
+response = completion(
+  model="nvidia_nim/<model_name>",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+)
+```
+
+</TabItem>
+
 <TabItem value="hugging" label="HuggingFace">
 
 ```python
@@ -274,6 +292,24 @@ response = completion(
 
 </TabItem>
 
+<TabItem value="nvidia" label="NVIDIA">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables
+os.environ["NVIDIA_NIM_API_KEY"] = "nvidia_api_key"
+os.environ["NVIDIA_NIM_API_BASE"] = "nvidia_nim_endpoint_url"
+
+response = completion(
+  model="nvidia_nim/<model_name>",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+  stream=True,
+)
+```
+</TabItem>
+
 <TabItem value="hugging" label="HuggingFace">
 
 ```python
diff --git a/docs/my-website/src/pages/index.md b/docs/my-website/src/pages/index.md
index 1b06dc592c..4a2e5203e3 100644
--- a/docs/my-website/src/pages/index.md
+++ b/docs/my-website/src/pages/index.md
@@ -108,6 +108,24 @@ response = completion(
 
 </TabItem>
 
+<TabItem value="nvidia" label="NVIDIA">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables
+os.environ["NVIDIA_NIM_API_KEY"] = "nvidia_api_key"
+os.environ["NVIDIA_NIM_API_BASE"] = "nvidia_nim_endpoint_url"
+
+response = completion(
+  model="nvidia_nim/<model_name>",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+)
+```
+
+</TabItem>
+
 <TabItem value="hugging" label="HuggingFace">
 
 ```python
@@ -238,6 +256,24 @@ response = completion(
 
 </TabItem>
 
+<TabItem value="nvidia" label="NVIDIA">
+
+```python
+from litellm import completion
+import os
+
+## set ENV variables
+os.environ["NVIDIA_NIM_API_KEY"] = "nvidia_api_key"
+os.environ["NVIDIA_NIM_API_BASE"] = "nvidia_nim_endpoint_url"
+
+response = completion(
+  model="nvidia_nim/<model_name>",
+  messages=[{ "content": "Hello, how are you?","role": "user"}]
+  stream=True,
+)
+```
+</TabItem>
+
 <TabItem value="hugging" label="HuggingFace">
 
 ```python