Skip to content

Commit

Permalink
feat: Updated docs/source/index.rst
Browse files Browse the repository at this point in the history
  • Loading branch information
sweep-ai[bot] committed Dec 21, 2023
1 parent adab66a commit 13cf3d8
Showing 1 changed file with 69 additions and 0 deletions.
69 changes: 69 additions & 0 deletions docs/source/index.rst
Original file line number Diff line number Diff line change
@@ -1,3 +1,16 @@
===========

.. image:: docs/images/DSPy8.png
:align: center
:width: 460px

DSPy: *Programming*—not prompting—Foundation Models
----------------------------------------------------

(links to paper and iamges from readme)

**DSPy** is the framework for solving advanced tasks with language models (LMs) and retrieval models (RMs). **DSPy** unifies techniques for **prompting** and **fine-tuning** LMs — and approaches for **reasoning**, **self-improvement**, and **augmentation with retrieval and tools**. All of these are expressed through modules that compose and learn.
=======
.. _index:

DSPy
Expand All @@ -14,6 +27,62 @@ DSPy: *Programming*—not prompting—Foundation Models

**DSPy** is the framework for solving advanced tasks with language models (LMs) and retrieval models (RMs). **DSPy** unifies techniques for **prompting** and **fine-tuning** LMs — and approaches for **reasoning**, **self-improvement**, and **augmentation with retrieval and tools**. All of these are expressed through modules that compose and learn.

.. toctree::
:maxdepth: 2
:caption: Table of Contents

language_models_client
retrieval_models_client
using_local_models
modules
teleprompters
==================

.. image:: docs/images/DSPy8.png
:align: center
:width: 460px

DSPy: *Programming*—not prompting—Foundation Models
----------------------------------------------------

(links to paper and iamges from readme)

**DSPy** is the framework for solving advanced tasks with language models (LMs) and retrieval models (RMs). **DSPy** unifies techniques for **prompting** and **fine-tuning** LMs — and approaches for **reasoning**, **self-improvement**, and **augmentation with retrieval and tools**. All of these are expressed through modules that compose and learn.
Language Model Clients
----------------------

Language Model Clients are interfaces for interacting with various language models. They provide a unified API for different language models, allowing you to switch between different models with minimal code changes.

For more details, see :doc:`language_models_client`.

Retrieval Model Clients
-----------------------

Retrieval Model Clients are interfaces for interacting with various retrieval models. They provide a unified API for different retrieval models, allowing you to switch between different models with minimal code changes.

For more details, see :doc:`retrieval_models_client`.

Using Local Models
------------------

DSPy supports various methods for loading local models. This includes built-in wrappers, server integration, and external package integration.

For more details, see :doc:`using_local_models`.

Modules
-------

Modules in DSPy are composable and declarative components that encapsulate specific functionality. They can be combined to create complex programs.

For more details, see :doc:`modules`.

Teleprompters
-------------

Teleprompters in DSPy are powerful optimizers that can learn to bootstrap and select effective prompts for the modules of any program.

For more details, see :doc:`teleprompters`.

To make this possible:

- **DSPy** provides **composable and declarative modules** for instruct

0 comments on commit 13cf3d8

Please sign in to comment.