kani now supports streaming to print tokens from the engine as they are received! Streaming is designed to be a drop-in superset of the chat_round and full_round methods, allowing you to gradually refactor your code without ever leaving it in a broken state.
To request a stream from the engine, use Kani.chat_round_stream() or Kani.full_round_stream(). These methods will return a StreamManager, which you can use in different ways to consume the stream.
The simplest way to consume the stream is to iterate over it with async for, which will yield a stream of str.
# CHAT ROUND:
stream = ai.chat_round_stream("What is the airspeed velocity of an unladen swallow?")
async for token in stream:
print(token, end="")
msg = await stream.message()
# FULL ROUND:
async for stream in ai.full_round_stream("What is the airspeed velocity of an unladen swallow?"):
async for token in stream:
print(token, end="")
msg = await stream.message()
After a stream finishes, its contents will be available as a ChatMessage. You can retrieve the final message or BaseCompletion with:
The final ChatMessage may contain non-yielded tokens (e.g. a request for a function call). If the final message or completion is requested before the stream is iterated over, the stream manager will consume the entire stream.
[!TIP]
For compatibility and ease of refactoring, awaiting the stream itself will also return the message, i.e.:
msg = await ai.chat_round_stream("What is the airspeed velocity of an unladen swallow?")
(note the await that is not present in the above examples). This allows you to refactor your code by changing chat_round to chat_round_stream without other changes.
- msg = await ai.chat_round("What is the airspeed velocity of an unladen swallow?")
+ msg = await ai.chat_round_stream("What is the airspeed velocity of an unladen swallow?")
Resolves #30
New Models
kani now has bundled support for the following new models:
Although these models have built-in support, kani supports every chat model available on Hugging Face through transformers or llama.cpp using the new Prompt Pipelines feature (see below)!
Resolves #34
llama.cpp
To use GGUF-quantized versions of models, kani now supports the LlamaCppEngine, which uses the llama-cpp-python library to interface with the llama.cpp library. Any model with a GGUF version is compatible with this engine!
Prompt Pipelines
A prompt pipeline creates a reproducible pipeline for translating a list of ChatMessage into an engine-specific format using fluent-style chaining.
To build a pipeline, create an instance of PromptPipeline() and add steps by calling the step methods documented below. Most pipelines will end with a call to one of the terminals, which translates the intermediate form into the desired output format.
Pipelines come with a built-in explain() method to print a detailed explanation of the pipeline and multiple examples (selected based on the pipeline steps).
Here’s an example using the PromptPipeline to build a LLaMA 2 chat-style prompt:
from kani import PromptPipeline, ChatRole
LLAMA2_PIPELINE = (
PromptPipeline()
# System messages should be wrapped with this tag. We'll translate them to USER
# messages since a system and user message go together in a single [INST] pair.
.wrap(role=ChatRole.SYSTEM, prefix="<<SYS>>\n", suffix="\n<</SYS>>\n")
.translate_role(role=ChatRole.SYSTEM, to=ChatRole.USER)
# If we see two consecutive USER messages, merge them together into one with a
# newline in between.
.merge_consecutive(role=ChatRole.USER, sep="\n")
# Similarly for ASSISTANT, but with a space (kani automatically strips whitespace from the ends of
# generations).
.merge_consecutive(role=ChatRole.ASSISTANT, sep=" ")
# Finally, wrap USER and ASSISTANT messages in the instruction tokens. If our
# message list ends with an ASSISTANT message, don't add the EOS token
# (we want the model to continue the generation).
.conversation_fmt(
user_prefix="<s>[INST] ",
user_suffix=" [/INST]",
assistant_prefix=" ",
assistant_suffix=" </s>",
assistant_suffix_if_last="",
)
)
# We can see what this pipeline does by calling explain()...
LLAMA2_PIPELINE.explain()
# And use it in our engine to build a string prompt for the LLM.
prompt = LLAMA2_PIPELINE(ai.get_prompt())
Integration with HuggingEngine and LlamaCppEngine
Previously, to use a model with a different prompt format than the ones bundled with the library, one had to create a subclass of the HuggingEngine to implement the prompting scheme. With the release of Prompt Pipelines, you can now supply a PromptPipeline in addition to the model ID to use the HuggingEngine directly!
For example, the LlamaEngine (huggingface) is now equivalent to the following:
The OpenAIEngine now uses the official openai-python package. (Resolves #31)
This means that aiohttp is no longer a direct dependency, and the HTTPClient has been deprecated. For API-based models, we recommend using the httpx library.
Added arguments to the chat_in_terminal helper to control maximum width, echo user inputs, show function call arguments and results, and other interactive utilities (#33)
The HuggingEngine can now automatically determine a model's context length.
Added a warning message if an @ai_function is missing a docstring. (Resolves #37)
Breaking Changes
All kani models (e.g. ChatMessage) are no longer immutable. This means that you can edit the chat history directly, and token counting will still work correctly.
As the ctransformers library does not appear to be maintained, we have removed the CTransformersEngine and replaced it with the LlamaCppEngine.
The arguments to chat_in_terminal (except the first) are now keyword-only.
The arguments to HuggingEngine (except model_id, max_context_size, and prompt_pipeline) are now keyword-only.
Generation arguments for OpenAI models now take dictionaries rather than kani.engines.openai.models.* models. (If you aren't sure if you're affected by this, you probably aren't.)
It should be a painless upgrade from kani v0.x to kani v1.0! We tried our best to ensure that we didn't break any existing code. If you encounter any issues, please reach out on our Discord.
New Features
Streaming
kani now supports streaming to print tokens from the engine as they are received! Streaming is designed to be a drop-in superset of the
chat_roundandfull_roundmethods, allowing you to gradually refactor your code without ever leaving it in a broken state.To request a stream from the engine, use
Kani.chat_round_stream()orKani.full_round_stream(). These methods will return aStreamManager, which you can use in different ways to consume the stream.The simplest way to consume the stream is to iterate over it with async for, which will yield a stream of str.
After a stream finishes, its contents will be available as a
ChatMessage. You can retrieve the final message or BaseCompletion with:The final ChatMessage may contain non-yielded tokens (e.g. a request for a function call). If the final message or completion is requested before the stream is iterated over, the stream manager will consume the entire stream.
Resolves #30
New Models
kani now has bundled support for the following new models:
Hosted
Open Source
Although these models have built-in support, kani supports every chat model available on Hugging Face through
transformersorllama.cppusing the new Prompt Pipelines feature (see below)!Resolves #34
llama.cpp
To use GGUF-quantized versions of models, kani now supports the
LlamaCppEngine, which uses thellama-cpp-pythonlibrary to interface with thellama.cpplibrary. Any model with a GGUF version is compatible with this engine!Prompt Pipelines
A prompt pipeline creates a reproducible pipeline for translating a list of
ChatMessageinto an engine-specific format using fluent-style chaining.To build a pipeline, create an instance of
PromptPipeline()and add steps by calling the step methods documented below. Most pipelines will end with a call to one of the terminals, which translates the intermediate form into the desired output format.Pipelines come with a built-in
explain()method to print a detailed explanation of the pipeline and multiple examples (selected based on the pipeline steps).Here’s an example using the PromptPipeline to build a LLaMA 2 chat-style prompt:
Integration with HuggingEngine and LlamaCppEngine
Previously, to use a model with a different prompt format than the ones bundled with the library, one had to create a subclass of the
HuggingEngineto implement the prompting scheme. With the release of Prompt Pipelines, you can now supply aPromptPipelinein addition to the model ID to use theHuggingEnginedirectly!For example, the
LlamaEngine(huggingface) is now equivalent to the following:Resolves #32
Improvements
OpenAIEnginenow uses the officialopenai-pythonpackage. (Resolves #31)aiohttpis no longer a direct dependency, and theHTTPClienthas been deprecated. For API-based models, we recommend using thehttpxlibrary.chat_in_terminalhelper to control maximum width, echo user inputs, show function call arguments and results, and other interactive utilities (#33)HuggingEnginecan now automatically determine a model's context length.@ai_functionis missing a docstring. (Resolves #37)Breaking Changes
kanimodels (e.g.ChatMessage) are no longer immutable. This means that you can edit the chat history directly, and token counting will still work correctly.ctransformerslibrary does not appear to be maintained, we have removed theCTransformersEngineand replaced it with theLlamaCppEngine.chat_in_terminal(except the first) are now keyword-only.HuggingEngine(exceptmodel_id,max_context_size, andprompt_pipeline) are now keyword-only.kani.engines.openai.models.*models. (If you aren't sure if you're affected by this, you probably aren't.)It should be a painless upgrade from kani v0.x to kani v1.0! We tried our best to ensure that we didn't break any existing code. If you encounter any issues, please reach out on our Discord.