mirror of
https://github.com/deepset-ai/haystack.git
synced 2025-12-05 03:17:31 +00:00
docs: clean up docstrings of OpenAIChatGenerator (#8125)
* openaichatgen-docstrings * link update
This commit is contained in:
Daria Fokina
GitHub
parent
c7e29a83c1
commit
28141ec6b9
@ -22,17 +22,21 @@ logger = logging.getLogger(__name__)
|
||||
@component
|
||||
class OpenAIChatGenerator:
|
||||
"""
|
||||
A Chat Generator component that uses the OpenAI API to generate text.
|
||||
Completes chats using OpenAI's large language models (LLMs).
|
||||
|
||||
Enables text generation using OpenAI's large language models (LLMs). It supports `gpt-4` and `gpt-3.5-turbo`
|
||||
family of models accessed through the chat completions API endpoint.
|
||||
It works with the gpt-4 and gpt-3.5-turbo models and supports streaming responses
|
||||
from OpenAI API. It uses [ChatMessage](https://docs.haystack.deepset.ai/docs/data-classes#chatmessage)
|
||||
format in input and output.
|
||||
|
||||
Users can pass any text generation parameters valid for the `openai.ChatCompletion.create` method
|
||||
directly to this component via the `generation_kwargs` parameter in `__init__` or the `generation_kwargs`
|
||||
parameter in `run` method.
|
||||
You can customize how the text is generated by passing parameters to the
|
||||
OpenAI API. Use the `**generation_kwargs` argument when you initialize
|
||||
the component or when you run it. Any parameter that works with
|
||||
`openai.ChatCompletion.create` will work here too.
|
||||
|
||||
For more details on the parameters supported by the OpenAI API, refer to the OpenAI
|
||||
[documentation](https://platform.openai.com/docs/api-reference/chat).
|
||||
For details on OpenAI API parameters, see
|
||||
[OpenAI documentation](https://platform.openai.com/docs/api-reference/chat).
|
||||
|
||||
### Usage example
|
||||
|
||||
```python
|
||||
from haystack.components.generators.chat import OpenAIChatGenerator
|
||||
@ -56,17 +60,6 @@ class OpenAIChatGenerator:
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
Key Features and Compatibility:
|
||||
- Primary Compatibility: designed to work seamlessly with the OpenAI API Chat Completion endpoint and `gpt-4`
|
||||
and `gpt-3.5-turbo` family of models.
|
||||
- Streaming Support: supports streaming responses from the OpenAI API Chat Completion endpoint.
|
||||
- Customizability: supports all parameters supported by the OpenAI API Chat Completion endpoint.
|
||||
|
||||
Input and Output Format:
|
||||
- ChatMessage Format: this component uses the ChatMessage format for structuring both input and output,
|
||||
ensuring coherent and contextually relevant responses in chat-based text generation scenarios. Details on the
|
||||
ChatMessage format can be found at [here](https://docs.haystack.deepset.ai/v2.0/docs/data-classes#chatmessage).
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
@ -81,22 +74,23 @@ class OpenAIChatGenerator:
|
||||
max_retries: Optional[int] = None,
|
||||
):
|
||||
"""
|
||||
Initializes the OpenAIChatGenerator component.
|
||||
Creates an instance of OpenAIChatGenerator. Unless specified otherwise in `model`, uses OpenAI's GPT-3.5.
|
||||
|
||||
Creates an instance of OpenAIChatGenerator. Unless specified otherwise in the `model`, this is for OpenAI's
|
||||
GPT-3.5 model.
|
||||
|
||||
By setting the 'OPENAI_TIMEOUT' and 'OPENAI_MAX_RETRIES' you can change the timeout and max_retries parameters
|
||||
Before initializing the component, you can set the 'OPENAI_TIMEOUT' and 'OPENAI_MAX_RETRIES'
|
||||
environment variables to override the `timeout` and `max_retries` parameters respectively
|
||||
in the OpenAI client.
|
||||
|
||||
:param api_key: The OpenAI API key.
|
||||
You can set it with an environment variable `OPENAI_API_KEY`, or pass with this parameter
|
||||
during initialization.
|
||||
:param model: The name of the model to use.
|
||||
:param streaming_callback: A callback function that is called when a new token is received from the stream.
|
||||
The callback function accepts StreamingChunk as an argument.
|
||||
The callback function accepts [StreamingChunk](https://docs.haystack.deepset.ai/docs/data-classes#streamingchunk)
|
||||
as an argument.
|
||||
:param api_base_url: An optional base URL.
|
||||
:param organization: The Organization ID, defaults to `None`. See
|
||||
:param organization: Your organization ID, defaults to `None`. See
|
||||
[production best practices](https://platform.openai.com/docs/guides/production-best-practices/setting-up-your-organization).
|
||||
:param generation_kwargs: Other parameters to use for the model. These parameters are all sent directly to
|
||||
:param generation_kwargs: Other parameters to use for the model. These parameters are sent directly to
|
||||
the OpenAI endpoint. See OpenAI [documentation](https://platform.openai.com/docs/api-reference/chat) for
|
||||
more details.
|
||||
Some of the supported parameters:
|
||||
@ -104,7 +98,7 @@ class OpenAIChatGenerator:
|
||||
- `temperature`: What sampling temperature to use. Higher values mean the model will take more risks.
|
||||
Try 0.9 for more creative applications and 0 (argmax sampling) for ones with a well-defined answer.
|
||||
- `top_p`: An alternative to sampling with temperature, called nucleus sampling, where the model
|
||||
considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens
|
||||
considers the results of the tokens with top_p probability mass. For example, 0.1 means only the tokens
|
||||
comprising the top 10% probability mass are considered.
|
||||
- `n`: How many completions to generate for each prompt. For example, if the LLM gets 3 prompts and n is 2,
|
||||
it will generate two completions for each of the three prompts, ending up with 6 completions in total.
|
||||
@ -116,11 +110,11 @@ class OpenAIChatGenerator:
|
||||
- `logit_bias`: Add a logit bias to specific tokens. The keys of the dictionary are tokens, and the
|
||||
values are the bias to add to that token.
|
||||
:param timeout:
|
||||
Timeout for OpenAI Client calls, if not set it is inferred from the `OPENAI_TIMEOUT` environment variable
|
||||
or set to 30.
|
||||
Timeout for OpenAI client calls. If not set, it defaults to either the
|
||||
`OPENAI_TIMEOUT` environment variable, or 30 seconds.
|
||||
:param max_retries:
|
||||
Maximum retries to stablish contact with OpenAI if it returns an internal error, if not set it is inferred
|
||||
from the `OPENAI_MAX_RETRIES` environment variable or set to 5.
|
||||
Maximum number of retries to contact OpenAI after an internal error.
|
||||
If not set, it defaults to either the `OPENAI_MAX_RETRIES` environment variable, or set to 5.
|
||||
"""
|
||||
self.api_key = api_key
|
||||
self.model = model
|
||||
@ -190,14 +184,14 @@ class OpenAIChatGenerator:
|
||||
generation_kwargs: Optional[Dict[str, Any]] = None,
|
||||
):
|
||||
"""
|
||||
Invoke the text generation inference based on the provided messages and generation parameters.
|
||||
Invokes chat completion based on the provided messages and generation parameters.
|
||||
|
||||
:param messages: A list of ChatMessage instances representing the input messages.
|
||||
:param streaming_callback: A callback function that is called when a new token is received from the stream.
|
||||
:param generation_kwargs: Additional keyword arguments for text generation. These parameters will
|
||||
potentially override the parameters passed in the `__init__` method.
|
||||
For more details on the parameters supported by the OpenAI API, refer to the
|
||||
OpenAI [documentation](https://platform.openai.com/docs/api-reference/chat/create).
|
||||
override the parameters passed during component initialization.
|
||||
For details on OpenAI API parameters, see
|
||||
[OpenAI documentation](https://platform.openai.com/docs/api-reference/chat/create).
|
||||
|
||||
:returns:
|
||||
A list containing the generated responses as ChatMessage instances.
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user