Documentation · FAQ · Discord · Code Examples
Synalinks: A production-first LM framework built with decade old Deep Learning best practices
⭐ Help us reach more AI/ML engineers and grow the Synalinks community. Star this repo ⭐
To busy to read the documentation? Give LLM.md to your favorite LM provider.
Synalinks is an open-source framework that makes it easy to create, evaluate, train, and deploy industry-standard Language Models (LMs) applications. Synalinks follows the principle of progressive disclosure of complexity: meaning that simple workflows should be quick and easy, while arbitrarily advanced ones should be possible via a clear path that builds upon what you've already learned.
Synalinks is an adaptation of Keras 3 focused on neuro-symbolic systems and in-context reinforcement learning, an ensemble of techniques that enhance the LMs predictions and accuracy without changing the weights of the model. The goal of Synalinks is to facilitate the rapid setup of simple applications while providing the flexibility for researchers and advanced users to develop sophisticated systems.
Synalinks is designed for a diverse range of users, from professionals and AI researchers to students, independent developers, and hobbyists. It is suitable for anyone who wants to learn about AI by building/composing blocks or build solid foundations for enterprise-grade products. While a background in Machine Learning and Deep Learning can be advantageous — as Synalinks leverages design patterns from Keras, one of the most user-friendly and popular Deep Learning frameworks — it is not a prerequisite. Synalinks is designed to be accessible to anyone with programming skills in Python, making it a versatile and inclusive platform for AI development.
Developping a successful LM application in a profesional context, beyond stateless chatbots, is difficult and typically include:
- Building optimized prompts with examples/instructions at each step: Synalinks uses advanced In-Context Reinforcement Learning techniques to optimize each prompt of your workflow/agent.
- Pipelines that change over time: Easily edit your pipelines, re-run your training, and you're good to go.
- Ensuring the correctness of the LMs output: Synalinks combines constrained structured output with In-Context RL to ensure both format and content correctness.
- Async Optimization: Synalinks automatically optimizes your pipelines by detecting parallel processes, so you don't have to worry about it.
- Assessing the performance of your application: Synalinks provides built-in metrics and rewards to evaluate your workflows.
- Configuring Language & Embedding Models: Seamlessly integrate multiple LM providers like Ollama, OpenAI, Azure, Anthropic, Mistral or Groq.
- Documenting your ML workflows: Plot your workflows, training history, and evaluations; document everything.
- Versioning the prompts/pipelines: Each program is serializable into JSON so you can version it with git.
- Deploying REST APIs: Compatible out-of-the-box with FastAPI and FastMPC so your Data Scientists and Web Developers can stop tearing each other apart.
Synalinks can help you simplify these tasks by leveraging decade old practices in Deep Learning frameworks. We provide a comprehensive suite of tools and features designed to streamline the development process, making it easier to create, evaluate, train, document and deploy robust neuro-symbolic LMs applications.
uv pip install synalinksStart your project with
uv run synalinks initYou start from Input, you chain modules calls to specify the program's structure, and finally, you create your program from inputs and outputs:
import synalinks
import asyncio
class Query(synalinks.DataModel):
query: str = synalinks.Field(
description="The user query",
)
class AnswerWithThinking(synalinks.DataModel):
thinking: str = synalinks.Field(
description="Your step by step thinking",
)
answer: float = synalinks.Field(
description="The correct numerical answer",
)
async def main():
language_model = synalinks.LanguageModel(
model="ollama/mistral",
)
x0 = synalinks.Input(data_model=Query)
x1 = await synalinks.Generator(
data_model=AnswerWithThinking,
language_model=language_model,
)(x0)
program = synalinks.Program(
inputs=x0,
outputs=x1,
name="chain_of_thought",
description="Useful to answer in a step by step manner.",
)
if __name__ == "__main__":
asyncio.run(main())In that case, you should define your modules in __init__() and implement the program's structure in call().
Note: you can optionaly have a training argument (boolean), which you can use to specify a different behavior in training and inference.
import synalinks
import asyncio
class Query(synalinks.DataModel):
query: str = synalinks.Field(
description="The user query",
)
class AnswerWithThinking(synalinks.DataModel):
thinking: str = synalinks.Field(
description="Your step by step thinking process",
)
answer: float = synalinks.Field(
description="The correct numerical answer",
)
class ChainOfThought(synalinks.Program):
"""Useful to answer in a step by step manner.
The first line of the docstring is provided as description
for the program if not provided in the `super().__init__()`.
In a similar way the name is automatically infered based on
the class name if not provided.
"""
def __init__(
self,
language_model=None,
name=None,
description=None,
trainable=True,
):
super().__init__(
name=name,
description=description,
trainable=trainable,
)
self.answer = synalinks.Generator(
data_model=AnswerWithThinking,
language_model=language_model,
name=self.name+"_generator",
)
async def call(self, inputs, training=False):
if not inputs:
return None
x = await self.answer(inputs, training=training)
return x
def get_config(self):
config = {
"name": self.name,
"description": self.description,
"trainable": self.trainable,
}
language_model_config = \
{
"language_model": synalinks.saving.serialize_synalinks_object(
self.language_model
)
}
return {**config, **language_model_config}
@classmethod
def from_config(cls, config):
language_model = synalinks.saving.deserialize_synalinks_object(
config.pop("language_model")
)
return cls(language_model=language_model, **config)
async def main():
language_model = synalinks.LanguageModel(
model="ollama/mistral",
)
program = ChainOfThought(
language_model=language_model,
)
if __name__ == "__main__":
asyncio.run(main())This way of programming is recommended to encapsulate your application while providing an easy to use setup.
It is the recommended way for most users as it avoid making your program/agents from scratch.
In that case, you should implement only the __init__() and build() methods.
import synalinks
import asyncio
class Query(synalinks.DataModel):
query: str = synalinks.Field(
description="The user query",
)
class AnswerWithThinking(synalinks.DataModel):
thinking: str = synalinks.Field(
description="Your step by step thinking process",
)
answer: float = synalinks.Field(
description="The correct numerical answer",
)
async def main():
class ChainOfThought(synalinks.Program):
"""Useful to answer in a step by step manner."""
def __init__(
self,
language_model=None,
name=None,
description=None,
trainable=True,
):
super().__init__(
name=name,
description=description,
trainable=trainable,
)
self.language_model = language_model
async def build(self, inputs):
outputs = await synalinks.Generator(
data_model=AnswerWithThinking,
language_model=self.language_model,
)(inputs)
# Create your program using the functional API
super().__init__(
inputs=inputs,
outputs=outputs,
name=self.name,
description=self.description,
trainable=self.trainable,
)
language_model = synalinks.LanguageModel(
model="ollama/mistral",
)
program = ChainOfThought(
language_model=language_model,
)
if __name__ == "__main__":
asyncio.run(main())This allows you to not have to implement the call() and serialization methods
(get_config() and from_config()). The program will be built for any inputs the first time called.
In addition, Sequential is a special case of program where the program
is purely a stack of single-input, single-output modules.
import synalinks
import asyncio
class Query(synalinks.DataModel):
query: str = synalinks.Field(
description="The user query",
)
class AnswerWithThinking(synalinks.DataModel):
thinking: str = synalinks.Field(
description="Your step by step thinking",
)
answer: float = synalinks.Field(
description="The correct numerical answer",
)
async def main():
language_model = synalinks.LanguageModel(
model="ollama/mistral",
)
program = synalinks.Sequential(
[
synalinks.Input(
data_model=Query,
),
synalinks.Generator(
data_model=AnswerWithThinking,
language_model=language_model,
),
],
name="chain_of_thought",
description="Useful to answer in a step by step manner.",
)
if __name__ == "__main__":
asyncio.run(main())To print a tabular summary of your program:
program.summary()Or a plot (Useful to document your system):
synalinks.utils.plot_program(
program,
show_module_names=True,
show_trainable=True,
show_schemas=True,
)
To run your program use the following:
result = await program(
Query(query="What is the French city of aerospace?"),
)async def main():
# ... your program definition
(x_train, y_train), (x_test, y_test) = synalinks.datasets.gsm8k.load_data()
program.compile(
reward=synalinks.rewards.ExactMatch(in_mask=["answer"]),
optimizer=synalinks.optimizers.RandomFewShot()
)
batch_size=32
epochs=10
history = await program.fit(
x_train,
y_train,
validation_data=(x_test, y_test),
batch_size=batch_size,
epochs=epochs,
)
if __name__ == "__main__":
asyncio.run(main())
You can learn more by reading our documentation. If you have questions, the FAQ might help you.
Contributions are welcome, either for the implementation of additional modules, metrics, or optimizers. For more information, or help for implementing your ideas (or ones from a paper), please join our discord.
Beware that every additional metric/module/optimizer should be approved by the core team, we want to keep the library minimal and clean as possible to avoid an uncontrolled growth leading to bad software practices like in most current leading LM frameworks.
If you have specific feedbacks or features request we invite you to open an issue.
We collect usage and software performance information to enhance and catch errors as fast as possible in order to make the best experience for you. No private, personal or confidential information is recorded. To get the complete list of what we collect, and how to disable it, please read the following document.
Join our community to learn more about neuro-symbolic systems and the future of AI. We welcome the participation of people from very different backgrounds or education levels.
This work have been done under the supervision of François Chollet, the author of Keras. If this work is useful for your research please use the following bibtex entry:
@misc{sallami2025synalinks,
title={Synalinks},
author={Sallami, Yoan and Chollet, Fran\c{c}ois},
year={2025},
howpublished={\url{https://github.com/SynaLinks/Synalinks}},
}Synalinks would not be possible without the great work of the following open-source projects: