Conversational Applications

Synalinks is designed to handle conversational applications as well as query-based systems. In the case of a conversational applications, the input data model is a list of chat messages, and the output an individual chat message. The Program is in that case responsible of handling a single conversation turn.

sequenceDiagram
    participant User
    participant Program
    participant LLM

    User->>Program: ChatMessages [msg1, msg2, ...]
    Program->>LLM: Full conversation context
    LLM-->>Program: New response
    Program-->>User: ChatMessage (assistant)
    Note over User,Program: Add response to history
    User->>Program: ChatMessages [..., new_msg]

inputs = synalinks.Input(data_model=synalinks.ChatMessages)
outputs = await synalinks.Generator(
    language_model=language_model,
    streaming=False,
)(inputs)

program = synalinks.Program(
    inputs=inputs,
    outputs=outputs,
    name="simple_chatbot",
)

By default, if no data_model/schema is provided to the Generator it will output a ChatMessage like output. If the data model is None, then you can enable streaming.

To use the chatbot, pass a ChatMessages object with the conversation history:

input_messages = synalinks.ChatMessages(
    messages=[
        synalinks.ChatMessage(
            role="user",
            content="Hello! What is the capital of France?",
        )
    ]
)
response = await program(input_messages)

Note: Streaming is disabled during training and should only be used in the last Generator of your pipeline.

Key Takeaways

Conversational Flow Management: Synalinks effectively manages conversational applications by handling inputs as a list of chat messages and generating individual chat messages as outputs.
Streaming and Real-Time Interaction: Synalinks supports streaming for real-time interactions. However, streaming is disabled during training and should be used only in the final Generator.
Simple Setup: Just use ChatMessages as input data model and the Generator will handle the conversation context automatically.

Program Visualization

API References

Source

--8 < --"examples/6_conversational_applications.py:83"

Run log

The log below is the unedited combined output of running the example above with local models (ollama).

Full run log: examples/6_conversational_applications.log

Simple Chatbot Example
Running the chatbot...
{
  "role": "assistant",
  "content": "The capital of France is Paris."
}