kani (カニ) is a highly hackable microframework for chat-based language models with tool use/function calling. (NLP-OSS @ EMNLP 2023)
WrapperEngine to make writing wrapper extensions easierkani 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:
msg = await stream.message()
completion = await stream.completion()
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?")
Issue: #30
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 transformers or llama.cpp using the new Prompt Pipelines feature (see below)!
Issue: #34
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!
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())
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:
engine = HuggingEngine(
"meta-llama/Llama-2-7b-chat-hf",
prompt_pipeline=LLAMA2_PIPELINE
)
Issue: #32
OpenAIEngine now uses the official openai-python package. (#31)
aiohttp is no longer a direct dependency, and the HTTPClient has been deprecated. For API-based models, we recommend using the httpx library.chat_in_terminal helper to control maximum width, echo user inputs, show function call arguments and results, and other interactive utilities (#33)HuggingEngine can now automatically determine a model's context length.@ai_function is missing a docstring. (#37)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.ctransformers library does not appear to be maintained, we have removed the CTransformersEngine and replaced it with the LlamaCppEngine.chat_in_terminal (except the first) are now keyword-only.HuggingEngine (except model_id, max_context_size, and prompt_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.
Most likely the last release before v1.0! This update mostly contains improvements to chat_in_terminal to improve usability in interactive environments like Jupyter Notebook.
All arguments to chat_in_terminal except the Kani instance must now be keyword arguments; positional arguments are no longer accepted.
For example, chat_in_terminal(ai, 1, "!stop") must now be written chat_in_terminal(ai, rounds=1, stopword="!stop").
None as the user query in chat_round and full_round. This will request a new ASSISTANT message without adding a USER message to the chat history (e.g. to continue an unfinished generation).Added the following keyword args to chat_in_terminal to improve usability in interactive environments like Jupyter Notebook:
echo, show_function_args, and show_function_returns to True.max_context_length explicitlyalways_included_messages near the maximum context lengthAnthropicEngine
ToolCallError to a more general PromptError
ToolCallError yetcontent field might get omitted in certain requests, causing an API errorAs of Nov 6, 2023, OpenAI added the ability for a single assistant message to request calling multiple functions in
parallel, and wrapped all function calls in a ToolCall wrapper. In order to add support for this in kani while
maintaining backwards compatibility with OSS function calling models, a ChatMessage now actually maintains the
following internal representation:
ChatMessage.function_call is actually an alias for ChatMessage.tool_calls[0].function. If there is more
than one tool call in the message, when trying to access this property, kani will raise an exception.
To translate kani's FUNCTION message types to OpenAI's TOOL message types, the OpenAIEngine now performs a translation based on binding free tool call IDs to following FUNCTION messages deterministically.
To the kani end user, there should be no change to how functions are defined and called. One breaking change was necessary:
Kani.do_function_call and Kani.handle_function_call_exception now take an additional tool_call_id parameter, which may break overriding functions. The documentation has been updated to encourage overriders to handle *args, **kwargs to prevent this happening again.kani can now handle making multiple function calls in parallel if the model requests it. Rather than returning an ASSISTANT message with a single function_call, an engine can now return a list of tool_calls. kani will resolve these tool calls in parallel using asyncio, and add their results to the chat history in the order of the list provided.
Returning a single function_call will continue to work for backwards compatibility.
OpenAIChatMessages as input rather than kani.ChatMessage in order to better type-validate API requests