xorbitsai · aresnow1 · Oct 24, 2023 · Oct 19, 2023 · Oct 19, 2023 · Oct 19, 2023
diff --git a/doc/source/examples/ai_podcast.rst b/doc/source/examples/ai_podcast.rst
@@ -76,4 +76,4 @@ Chinese (AI_Podcast_ZH.py)
 
     * `AI_Podcast <https://github.com/xorbitsai/inference/blob/main/examples/AI_podcast.py>`_ (English Version)
 
-    * AI_Podcast_ZH (Chinese Version)
+    * `AI_Podcast_ZH <https://github.com/xorbitsai/inference/blob/main/examples/AI_podcast_ZH.py>` (Chinese Version)
diff --git a/doc/source/examples/chatbot.rst b/doc/source/examples/chatbot.rst
@@ -1,12 +1,12 @@
 .. _examples_chatbot:
 
-====================
-Example: chatbot 🤖️
-====================
+=======================
+Example: CLI chatbot 🤖️
+=======================
 
 **Description**:
 
-Demonstrate how to interact with Xinference to play with LLM chat functionality with an AI agent 💻
+Demonstrate how to interact with Xinference to play with LLM chat functionality with an AI agent in command line💻
 
 **Used Technology**:
 

diff --git a/doc/source/examples/gradio_chatinterface.rst b/doc/source/examples/gradio_chatinterface.rst
@@ -0,0 +1,30 @@
+.. _examples_gradio_chatinterface:
+
+==============================
+Example: Gradio ChatInterface🤗
+==============================
+
+**Description**:
+
+This example showcases how to build a chatbot with 120 lines of code with Gradio ChatInterface and Xinference local LLM
+
+**Used Technology**:
+
+    @ `Xinference <https://github.com/xorbitsai/inference>`_ as a LLM model hosting service
+
+    @ `Gradio <https://github.com/gradio-app/gradio>`_ as a web interface for the chatbot
+
+**Detailed Explanation on the Demo Functionality** :
+
+* Parse user-provided command line arguments to capture essential model parameters such as model name, size, format, and quantization.
+
+* Establish a connection to the Xinference framework and deploy the specified model, ensuring it's ready for real-time interactions.
+
+* Implement helper functions (flatten and to_chat) to efficiently handle and store chat interactions, ensuring the model has context for generating relevant responses.
+
+* Set up an interactive chat interface using Gradio, allowing users to communicate with the model in a user-friendly environment.
+
+* Activate the Gradio web interface, enabling users to start their chat sessions and receive model-generated responses based on their queries.
+
+**Source Code** :
+    * `Gradio ChatInterface <https://github.com/xorbitsai/inference/blob/main/examples/gradio_chatinterface.py>`_
diff --git a/doc/source/examples/index.rst b/doc/source/examples/index.rst
@@ -9,4 +9,50 @@ Examples
    :hidden:
 
    ai_podcast
-   chatbot
+   chatbot
+   gradio_chatinterface
+   pdf_chatbot
+
+Here you can find examples and resources to learn about how to use Xinference.
+
+Examples
+========
+
+End-to-end examples of using Xinference for various tasks:
+
+* `Voice Conversations with AI Agents on M2 Max <ai_podcast.html>`_
+
+* `Interacting with LLM Models: A Command-Line Example <chatbot.html>`_
+
+* `Interacting with LLM Models: A Gradio ChatInterface Example <gradio_chatinterface.html>`_
+
+* `PDF Chatbot with Local LLM and Embeddings <pdf_chatbot.html>`_ 
+
+If you come across other examples in your own workflows we encourage you to contribute a `PR <https://github.com/xorbitsai/inference/pulls>`_!
+
+
+Tutorials
+=========
+
+The following tutorials cover the basics of using Xinference in different scenarios:
+
+* `Build a QA Application with Xinference and LangChain <https://github.com/RayJi01/Xprobe_inference/blob/main/examples/LangChain_QA.ipynb>`_
+
+* `Using Xinference local LLMs within LlamaIndex <https://gpt-index.readthedocs.io/en/stable/examples/llm/XinferenceLocalDeployment.html>`_
+
+* `[Chinese] 如何让 Chatbox 接入开源大模型，实现免费聊天 <https://twitter.com/benn_huang/status/1701420060240490785>`_
+
+* `[Chinese] 摆脱 OpenAI 依赖，8 分钟教你用开源生态构建全栈 AI 应用 <https://mp.weixin.qq.com/s/cXBC0dikldNiGwOwPuJfUQ>`_
+
+* `[Chinese] 使用全套开源工具构建 LLM 应用实战 <https://mp.weixin.qq.com/s/regqYkF0cNDQIdOkOeyeXQ>`_
+
+
+Third-Party Library Integrations
+================================
+
+Xinference is designed to seamlessly integrate and deploy open-sourced AI models, so we want to incorporate support for mainstream toolkits
+in the AI landscape. Xinference can be used with the following third-party libraries:
+
+* LangChain `Text Embedding Models <https://python.langchain.com/docs/integrations/text_embedding/xinference>`_ and `LLMs <https://python.langchain.com/docs/integrations/llms/xinference>`_
+
+* `LlamaIndex Xinference LLM <https://docs.llamaindex.ai/en/stable/api_reference/llms/xinference.html>`_
diff --git a/doc/source/examples/pdf_chatbot.rst b/doc/source/examples/pdf_chatbot.rst
@@ -0,0 +1,32 @@
+.. _examples_pdf_chatbot:
+
+======================
+Example: PDF Chatbot📚
+======================
+
+**Description**:
+
+This example showcases how to build a PDF chatbot with local LLM and Embedding models
+
+**Used Technology**:
+
+    @ `Xinference <https://github.com/xorbitsai/inference>`_ as a LLM model hosting service
+
+    @ `LlamaIndex <https://github.com/run-llama/llama_index>`_ for orchestrating the entire RAG pipeline 
+
+    @ `Streamlit <https://streamlit.io/>`_ for interactive UI
+
+**Detailed Explanation on the Demo Functionality** :
+
+* Crafted a Dockerfile to simplify the process and ensure easy reproducibility.
+
+* Set up models with Xinference and expose two ports for accessing them.
+
+* Leverage Streamlit for seamless file uploads and interactive communication with the chat engine.
+
+* 5x faster doc embedding than OpenAI's API.
+
+* Leveraging the power of GGML to offload models to the GPU, ensuring swift acceleration. Less long waits for returns.
+
+**Source Code** :
+    * `PDF Chatbot <https://github.com/onesuper/PDF-Chatbot-Local-LLM-Embeddings>`_
Original file line number	Diff line number	Diff line change
Expand Up		@@ -76,4 +76,4 @@ Chinese (AI_Podcast_ZH.py)

		* `AI_Podcast <https://github.com/xorbitsai/inference/blob/main/examples/AI_podcast.py>`_ (English Version)

		* AI_Podcast_ZH (Chinese Version)
		* `AI_Podcast_ZH <https://github.com/xorbitsai/inference/blob/main/examples/AI_podcast_ZH.py>` (Chinese Version)