Skip to content

Commit

Permalink
reorganize sample guides, add CodeGen top sample guide
Browse files Browse the repository at this point in the history
Signed-off-by: alexsin368 <[email protected]>
  • Loading branch information
alexsin368 committed Nov 20, 2024
1 parent 112db28 commit 3d9f9c0
Show file tree
Hide file tree
Showing 2 changed files with 49 additions and 3 deletions.
48 changes: 48 additions & 0 deletions examples/CodeGen/CodeGen_Guide.rst
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
.. _Codegen_Guide:

Codegen Sample Guide
#####################

.. note:: This guide is in its early development and is a work-in-progress with
placeholder content.

Overview
********

The CodeGen example uses specialized AI models that went through training with datasets that
encompass repositories, documentation, programming code, and web data. With an understanding
of various programming languages, coding patterns, and software development concepts, the
CodeGen LLMs assist developers and programmers. The LLMs can be integrated into the developers'
Integrated Development Environments (IDEs) to have more contextual awareness to write more
refined and relevant code based on the suggestions.

Purpose
*******
* Code Generation: Streamline coding through Code Generation, enabling non-programmers to describe tasks for code creation.
* Code Completion: Accelerate coding by suggesting contextually relevant snippets as developers type.
* Code Translation and Modernization: Translate and modernize code across multiple programming languages, aiding interoperability and updating legacy projects.
* Code Summarization: Extract key insights from codebases, improving readability and developer productivity.
* Code Refactoring: Offer suggestions for code refactoring, enhancing code performance and efficiency.
* AI-Assisted Testing: Assist in creating test cases, ensuring code robustness and accelerating development cycles.
* Error Detection and Debugging: Detect errors in code and provide detailed descriptions and potential fixes, expediting debugging processes.

How It Works
************

The CodeGen example uses an open-source code generation model with Text Generation Inference (TGI)
for serving deployment. It is presented as a Code Copilot application as shown in the diagram below.

.. figure:: /GenAIExamples/CodeGen/assets/img/codegen_architecture.png
:alt: CodeGen Architecture Diagram

Deployment
**********
Here are some deployment options, depending on your hardware and environment:

Single Node
+++++++++++++++
.. toctree::
:maxdepth: 1

Xeon Scalable Processor </GenAIExamples/CodeGen/docker_compose/intel/cpu/xeon/README.md>
Gaudi AI Accelerator <deploy/gaudi>
4 changes: 1 addition & 3 deletions examples/index.rst
Original file line number Diff line number Diff line change
Expand Up @@ -9,10 +9,8 @@ GenAIExamples are designed to give developers an easy entry into generative AI,
:maxdepth: 1

ChatQnA/ChatQnA_Guide
ChatQnA/deploy/index
AgentQnA/AgentQnA_Guide
CodeGen/deploy/gaudi.md
CodeGen/deploy/index
CodeGen/CodeGen_Guide

----

Expand Down

0 comments on commit 3d9f9c0

Please sign in to comment.