From b80b074de9b210c9dfbe07bada78d0eaa7c87c9f Mon Sep 17 00:00:00 2001
From: amitamrutiya2210 <amitamrutiya2210@gmail.com>
Date: Sat, 24 Feb 2024 10:52:57 +0530
Subject: [PATCH] docs: add documentation for the newly added hugging face
 provider

Signed-off-by: amitamrutiya2210 <amitamrutiya2210@gmail.com>
---
 docs/reference/providers/backend.md | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/docs/reference/providers/backend.md b/docs/reference/providers/backend.md
index caccf49..749385d 100644
--- a/docs/reference/providers/backend.md
+++ b/docs/reference/providers/backend.md
@@ -10,6 +10,7 @@ Currently, we have a total of 8 backends available:
 - [Amazon SageMaker](https://aws.amazon.com/sagemaker/)
 - [Azure OpenAI](https://azure.microsoft.com/en-us/products/cognitive-services/openai-service)
 - [Google Gemini](https://ai.google.dev/docs/gemini_api_overview)
+- [Hugging Face](https://huggingface.co)
 - [LocalAI](https://github.com/go-skynet/LocalAI)
 - FakeAI
 
@@ -23,7 +24,7 @@ OpenAI is the default backend for K8sGPT. We recommend using OpenAI first if you
     ```
 - To set the token in K8sGPT, use the following command:
     ```bash
-    k8sgpt auth add 
+    k8sgpt auth add
     ```
 - Run the following command to analyze issues within your cluster using OpenAI:
     ```bash
@@ -117,6 +118,22 @@ Google [Gemini](https://blog.google/technology/ai/google-gemini-ai/#performance)
     k8sgpt analyze --explain --backend google
     ```
 
+## HuggingFace
+
+Hugging Face is a versatile backend for K8sGPT, offering access to a wide range of pre-trained language models. It provides easy-to-use interfaces for both training and inference tasks. Refer to the Hugging Face [documentation](https://huggingface.co/docs) for further insights into model usage and capabilities.
+
+- To use Hugging Face API in K8sGPT, obtain [the API key](https://huggingface.co/settings/tokens).
+- Configure the HuggingFace backend in K8sGPT by specifying the desired model (see all [models](https://huggingface.co/models) here) using auth command:
+    ```bash
+    k8sgpt auth add --backend huggingface --model <model name>
+    ```
+> NOTE: Since the default gpt-3.5-turbo model is not available in Hugging Face, a valid backend model is required.
+
+- Once configured, you can analyze issues within your cluster using the Hugging Face provider with the following command:
+    ```bash
+    k8sgpt analyze --explain --backend huggingface
+    ```
+
 ## LocalAI
 
 LocalAI is a local model, which is an OpenAI compatible API. It uses llama.cpp and ggml to run inference on consumer-grade hardware. Models supported by LocalAI for instance are Vicuna, Alpaca, LLaMA, Cerebras, GPT4ALL, GPT4ALL-J and koala.