Merge pull request #177 from SylphAI-Inc/main

update the package and links in tutorials to adalflow from lightrag

CNAME

@@ -1 +1 @@
-lightrag.sylph.ai
+adalflow.sylph.ai

README.md

@@ -16,10 +16,11 @@
 
 <h4 align="center">
     <p>
-        <a href="https://lightrag.sylph.ai/">Documentation</a> |
-        <a href="https://lightrag.sylph.ai/apis/components/components.model_client.html">Models</a> |
-        <a href="https://lightrag.sylph.ai/apis/components/components.retriever.html">Retrievers</a> |
-        <a href="https://lightrag.sylph.ai/apis/components/components.agent.html">Agents</a>
+        <a href="https://adalflow.sylph.ai/">All Documentation</a> |
+        <a href="https://adalflow.sylph.ai/apis/components/components.model_client.html">Models</a> |
+        <a href="https://adalflow.sylph.ai/apis/components/components.retriever.html">Retrievers</a> |
+        <a href="https://adalflow.sylph.ai/apis/components/components.agent.html">Agents</a> |
+        <a href="https://adalflow.sylph.ai/use_cases/question_answering.html">Trainer & Optimizers</a>
     <p>
 </h4>
 
@@ -53,11 +54,12 @@
 
 
 
-<h1>
+<h2>
     <p align="center">
-        AdalFlow: The Library to Build and to Auto-optimize LLM Applications
+     ⚡ The Library to Build and to Auto-optimize LLM Applications ⚡
     </p>
-</h1>
+</h2>
+
 
 AdalFlow helps developers build and optimize LLM task pipelines.
 Embracing similar design pattern to PyTorch, AdalFlow is light, modular, and robust, with a 100% readable codebase.
@@ -73,7 +75,7 @@ Because of this, no library can provide out-of-the-box solutions. Users must bui
 
 
 Further reading: [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop),
-[Introduction](https://lightrag.sylph.ai/), [Design Philosophy](https://lightrag.sylph.ai/tutorials/lightrag_design_philosophy.html) and [Class hierarchy](https://lightrag.sylph.ai/tutorials/class_hierarchy.html).
+[Introduction](https://adalflow.sylph.ai/), [Design Philosophy](https://adalflow.sylph.ai/tutorials/lightrag_design_philosophy.html) and [Class hierarchy](https://adalflow.sylph.ai/tutorials/class_hierarchy.html).
 
 
 <!--
@@ -261,7 +263,7 @@ You can switch to any model simply by using a different `model_client` (provider
 Let's use OpenAI's `gpt-3.5-turbo` model.
 
 ```python
-from lightrag.components.model_client import OpenAIClient
+from adalflow.components.model_client import OpenAIClient
 
 self.generator = Generator(
     model_client=OpenAIClient(),
@@ -281,23 +283,23 @@ Install AdalFlow with pip:
 pip install adalflow
 ```
 
-Please refer to the [full installation guide](https://lightrag.sylph.ai/get_started/installation.html) for more details.
+Please refer to the [full installation guide](https://adalflow.sylph.ai/get_started/installation.html) for more details.
 
 
 
 
 # Documentation
 
-AdalFlow full documentation available at [lightrag.sylph.ai](https://lightrag.sylph.ai/):
+AdalFlow full documentation available at [adalflow.sylph.ai](https://adalflow.sylph.ai/):
 - [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop)
-- [Introduction](https://lightrag.sylph.ai/)
-- [Full installation guide](https://lightrag.sylph.ai/get_started/installation.html)
-- [Design philosophy](https://lightrag.sylph.ai/tutorials/lightrag_design_philosophy.html)
-- [Class hierarchy](https://lightrag.sylph.ai/tutorials/class_hierarchy.html)
-- [Tutorials](https://lightrag.sylph.ai/tutorials/index.html)
-- [Supported Models](https://lightrag.sylph.ai/apis/components/components.model_client.html)
-- [Supported Retrievers](https://lightrag.sylph.ai/apis/components/components.retriever.html)
-- [API reference](https://lightrag.sylph.ai/apis/index.html)
+- [Introduction](https://adalflow.sylph.ai/)
+- [Full installation guide](https://adalflow.sylph.ai/get_started/installation.html)
+- [Design philosophy](https://adalflow.sylph.ai/tutorials/lightrag_design_philosophy.html)
+- [Class hierarchy](https://adalflow.sylph.ai/tutorials/class_hierarchy.html)
+- [Tutorials](https://adalflow.sylph.ai/tutorials/index.html)
+- [Supported Models](https://adalflow.sylph.ai/apis/components/components.model_client.html)
+- [Supported Retrievers](https://adalflow.sylph.ai/apis/components/components.retriever.html)
+- [API reference](https://adalflow.sylph.ai/apis/index.html)
 
 
 # AdalFlow: A Tribute to Ada Lovelace

adalflow/CHANGELOG.md

@@ -1,3 +1,7 @@
+## [0.2.0.beta.3] - 2024-08-16
+### Fixed
+- missing `diskcache` package in the dependencies.
+
 ## [0.2.0.beta.2] - 2024-08-15
 ### Improved
 - ``Demo Optimizer`` with "learn-to-reason" one shot to achieve 94% on the object count, close to the 98% by the teacher gpt-4o model.

adalflow/README.md

@@ -16,16 +16,17 @@
 
 <h4 align="center">
     <p>
-        <a href="https://lightrag.sylph.ai/">Documentation</a> |
-        <a href="https://lightrag.sylph.ai/apis/components/components.model_client.html">Models</a> |
-        <a href="https://lightrag.sylph.ai/apis/components/components.retriever.html">Retrievers</a> |
-        <a href="https://lightrag.sylph.ai/apis/components/components.agent.html">Agents</a>
+        <a href="https://adalflow.sylph.ai/">All Documentation</a> |
+        <a href="https://adalflow.sylph.ai/apis/components/components.model_client.html">Models</a> |
+        <a href="https://adalflow.sylph.ai/apis/components/components.retriever.html">Retrievers</a> |
+        <a href="https://adalflow.sylph.ai/apis/components/components.agent.html">Agents</a> |
+        <a href="https://adalflow.sylph.ai/use_cases/question_answering.html">Trainer & Optimizers</a>
     <p>
 </h4>
 
 <p align="center">
-    <a href="https://pypi.org/project/lightRAG">
-        <img alt="PyPI Version" src="https://img.shields.io/pypi/v/lightRAG?style=flat-square">
+    <a href="https://pypi.org/project/adalflow/">
+        <img alt="PyPI Version" src="https://img.shields.io/pypi/v/adalflow?style=flat-square">
     </a>
     <a href="https://star-history.com/#SylphAI-Inc/LightRAG">
         <img alt="GitHub stars" src="https://img.shields.io/github/stars/SylphAI-Inc/LightRAG?style=flat-square">
@@ -53,20 +54,17 @@
 
 
 
-<h1>
+<h2>
     <p align="center">
-        AdalFlow: The Library for LLM Applications
+     ⚡ The Library to Build and to Auto-optimize LLM Applications ⚡
     </p>
-</h1>
+</h2>
+
 
 AdalFlow helps developers build and optimize LLM task pipelines.
 Embracing similar design pattern to PyTorch, AdalFlow is light, modular, and robust, with a 100% readable codebase.
 
 
-# AdalFlow: A Tribute to Ada Lovelace
-
-AdalFlow is named in honor of [Ada Lovelace](https://en.wikipedia.org/wiki/Ada_Lovelace), the pioneering female mathematician who first recognized that machines could do more than just calculations. As a female-led team, we aim to inspire more women to enter the AI field.
-
 # Why AdalFlow?
 
 LLMs are like water; they can be shaped into anything, from GenAI applications such as chatbots, translation, summarization, code generation, and autonomous agents to classical NLP tasks like text classification and named entity recognition. They interact with the world beyond the model’s internal knowledge via retrievers, memory, and tools (function calls). Each use case is unique in its data, business logic, and user experience.
@@ -77,7 +75,7 @@ Because of this, no library can provide out-of-the-box solutions. Users must bui
 
 
 Further reading: [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop),
-[Introduction](https://lightrag.sylph.ai/), [Design Philosophy](https://lightrag.sylph.ai/tutorials/lightrag_design_philosophy.html) and [Class hierarchy](https://lightrag.sylph.ai/tutorials/class_hierarchy.html).
+[Introduction](https://adalflow.sylph.ai/), [Design Philosophy](https://adalflow.sylph.ai/tutorials/lightrag_design_philosophy.html) and [Class hierarchy](https://adalflow.sylph.ai/tutorials/class_hierarchy.html).
 
 
 <!--
@@ -265,7 +263,7 @@ You can switch to any model simply by using a different `model_client` (provider
 Let's use OpenAI's `gpt-3.5-turbo` model.
 
 ```python
-from lightrag.components.model_client import OpenAIClient
+from adalflow.components.model_client import OpenAIClient
 
 self.generator = Generator(
     model_client=OpenAIClient(),
@@ -285,26 +283,28 @@ Install AdalFlow with pip:
 pip install adalflow
 ```
 
-Please refer to the [full installation guide](https://lightrag.sylph.ai/get_started/installation.html) for more details.
+Please refer to the [full installation guide](https://adalflow.sylph.ai/get_started/installation.html) for more details.
 
 
 
 
 # Documentation
 
-AdalFlow full documentation available at [lightrag.sylph.ai](https://lightrag.sylph.ai/):
+AdalFlow full documentation available at [adalflow.sylph.ai](https://adalflow.sylph.ai/):
 - [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop)
-- [Introduction](https://lightrag.sylph.ai/)
-- [Full installation guide](https://lightrag.sylph.ai/get_started/installation.html)
-- [Design philosophy](https://lightrag.sylph.ai/tutorials/lightrag_design_philosophy.html)
-- [Class hierarchy](https://lightrag.sylph.ai/tutorials/class_hierarchy.html)
-- [Tutorials](https://lightrag.sylph.ai/tutorials/index.html)
-- [Supported Models](https://lightrag.sylph.ai/apis/components/components.model_client.html)
-- [Supported Retrievers](https://lightrag.sylph.ai/apis/components/components.retriever.html)
-- [API reference](https://lightrag.sylph.ai/apis/index.html)
+- [Introduction](https://adalflow.sylph.ai/)
+- [Full installation guide](https://adalflow.sylph.ai/get_started/installation.html)
+- [Design philosophy](https://adalflow.sylph.ai/tutorials/lightrag_design_philosophy.html)
+- [Class hierarchy](https://adalflow.sylph.ai/tutorials/class_hierarchy.html)
+- [Tutorials](https://adalflow.sylph.ai/tutorials/index.html)
+- [Supported Models](https://adalflow.sylph.ai/apis/components/components.model_client.html)
+- [Supported Retrievers](https://adalflow.sylph.ai/apis/components/components.retriever.html)
+- [API reference](https://adalflow.sylph.ai/apis/index.html)
 
 
+# AdalFlow: A Tribute to Ada Lovelace
 
+AdalFlow is named in honor of [Ada Lovelace](https://en.wikipedia.org/wiki/Ada_Lovelace), the pioneering female mathematician who first recognized that machines could do more than just calculations. As a female-led team, we aim to inspire more women to enter the AI field.
 
 # Contributors
 

adalflow/adalflow/__init__.py

@@ -1,8 +1,8 @@
-__version__ = "0.2.0-beta.2"
+__version__ = "0.2.0-beta.3"
 
 from adalflow.core.component import Component, fun_to_component
+from adalflow.core.container import Sequential
 
-# from adalflow.core.container import Sequential
 from adalflow.optim.grad_component import GradComponent
 from adalflow.core.generator import Generator
 from adalflow.core.types import GeneratorOutput, EmbedderOutput, RetrieverOutput
@@ -41,6 +41,7 @@
 __all__ = [
     "Component",
     "fun_to_component",
+    "Sequential",
     "GradComponent",
     "ModelClient",
     "Generator",

adalflow/adalflow/core/generator.py

@@ -813,7 +813,12 @@ async def acall(
                 output = GeneratorOutput(raw_response=str(completion), error=str(e))
 
         log.info(f"output: {output}")
-        self._run_callbacks(output, input=api_kwargs)
+        self._run_callbacks(
+            output,
+            input=api_kwargs,
+            prompt_kwargs=prompt_kwargs,
+            model_kwargs=model_kwargs,
+        )
         return output
 
     def __call__(self, *args, **kwargs) -> Union[GeneratorOutputType, Any]:

adalflow/pyproject.toml

@@ -1,8 +1,8 @@
 [tool.poetry]
 name = "adalflow"
 
-version = "0.2.0.beta.2"
-description = "The Library for LLM Applications."
+version = "0.2.0.beta.3"
+description = "The Library to Build and Auto-optimize Any LLM Task Pipeline"
 authors = ["Li Yin <[email protected]>"]
 readme = "README.md"
 repository = "https://github.com/SylphAI-Inc/LightRAG"
@@ -57,6 +57,7 @@ anthropic = { version = "^0.31.1", optional = true }
 google-generativeai = { version = "^0.7.2", optional = true }
 cohere = { version = "^5.5.8", optional = true }
 ollama = { version = "^0.2.1", optional = true }
+diskcache = "^5.6.3"
 
 
 [tool.poetry.group.test.dependencies]

docs/source/get_started/installation.rst

@@ -50,7 +50,7 @@ You can use the following import:
 
 .. code-block:: python
 
-   from lightrag.utils import setup_env
+   from adalflow.utils import setup_env
 
    setup_env()
 

docs/source/index.rst

@@ -35,7 +35,9 @@
 
 .. raw:: html
 
-    <h3 style="text-align: center; font-size: 1.5em; margin-top: 10px;">⚡ The Library to Build and to Auto-optimize Large Language Model Applications ⚡</h3>
+    <h3 style="text-align: center; font-size: 1.5em; margin-top: 10px;">
+    ⚡ The Library to Build and to Auto-optimize Any LLM Task Pipeline ⚡
+    </h3>
 
 ..  <div style="text-align: center;">
 ..      <p>
@@ -98,11 +100,11 @@ We provide developers with fundamental building blocks of *100% clarity and simp
 
       .. code-block:: python
 
-         from lightrag.core import Component, Generator
-         from lightrag.components.model_client import GroqAPIClient
+         import adalflow as adal
+         from adalflow.components.model_client import GroqAPIClient
 
 
-         class SimpleQA(Component):
+         class SimpleQA(adal.Component):
             def __init__(self):
                super().__init__()
                template = r"""<SYS>
@@ -111,7 +113,7 @@ We provide developers with fundamental building blocks of *100% clarity and simp
                User: {{input_str}}
                You:
                """
-               self.generator = Generator(
+               self.generator = adal.Generator(
                      model_client=GroqAPIClient(),
                      model_kwargs={"model": "llama3-8b-8192"},
                      template=template,
@@ -163,9 +165,9 @@ To switch to `gpt-3.5-turbo` by OpenAI, simply update the `model_client`` and `m
 
 .. code-block:: python
 
-   from lightrag.components.model_client import OpenAIClient
+   from adalflow.components.model_client import OpenAIClient
 
-   self.generator = Generator(
+   self.generator = adal.Generator(
         model_client=OpenAIClient(),
         model_kwargs={"model": "gpt-3.5-turbo"},
         template=template,