id
stringlengths
14
16
text
stringlengths
31
3.14k
source
stringlengths
58
124
09c7c6e2de63-47
Return a dictionary of the LLM. generate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prompt and input. generate_prompt(prompts: List[langchain.schema.PromptValue], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Take in a list of prompt va...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-48
encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps(). save(file_path: Union[pathlib.Path, str]) → None# Save the LLM. Parameters file_path – Path to file to save the LLM to. Example: .. code-block:: python llm.save(file_path=”path/llm.yaml”) classmethod update_forwar...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-49
Task to call the model with. Should be a task that returns generated_text. __call__(prompt: str, stop: Optional[List[str]] = None) → str# Check Cache and run the LLM on the given prompt and input. async agenerate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the give...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-50
Parameters include – fields to include in new model exclude – fields to exclude from new model, as with values this takes precedence over include update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data deep – set to True to make a deep co...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-51
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-52
To use, you should have the transformers python package installed. Only supports text-generation and text2text-generation for now. Example using from_model_id:from langchain.llms import HuggingFacePipeline hf = HuggingFacePipeline.from_model_id( model_id="gpt2", task="text-generation" ) Example passing pipeline in ...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-53
Run the LLM on the given prompt and input. async agenerate_prompt(prompts: List[langchain.schema.PromptValue], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Take in a list of prompt values and return an LLMResult. classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model# Crea...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-54
Return a dictionary of the LLM. classmethod from_model_id(model_id: str, task: str, device: int = - 1, model_kwargs: Optional[dict] = None, **kwargs: Any) → langchain.llms.base.LLM[source]# Construct the pipeline object from model_id and task. generate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.s...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-55
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-56
path to the Llama model as a named parameter to the constructor. Check out: abetlen/llama-cpp-python Example from langchain.llms import LlamaCppEmbeddings llm = LlamaCppEmbeddings(model_path="/path/to/llama/model") Validators set_callback_manager » callback_manager set_verbose » verbose validate_environment » all field...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-57
field n_ctx: int = 512# Token context window. field n_parts: int = -1# Number of parts to split the model into. If -1, the number of parts is automatically determined. field n_threads: Optional[int] = None# Number of threads to use. If None, the number of threads is automatically determined. field repeat_penalty: Optio...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-58
Check Cache and run the LLM on the given prompt and input. async agenerate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prompt and input. async agenerate_prompt(prompts: List[langchain.schema.PromptValue], stop: Optional[List[str]] = None) → langchain.sche...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-59
the new model: you should trust this data deep – set to True to make a deep copy of the model Returns new model instance dict(**kwargs: Any) → Dict# Return a dictionary of the LLM. generate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prompt and input. gen...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-60
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-61
Once that happens, this interface could change. It also calls the callback manager’s on_llm_new_token event with similar parameters to the OpenAI LLM class method of the same name. Args:prompt: The prompts to pass into the model. stop: Optional list of stop words to use when generating. Returns:A generator representing...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-62
field endpoint_url: str = ''# model endpoint to use field model_kwargs: Dict[str, Any] [Optional]# Holds any model parameters valid for create call not explicitly specified. __call__(prompt: str, stop: Optional[List[str]] = None) → str# Check Cache and run the LLM on the given prompt and input. async agenerate(prompts:...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-63
Duplicate a model, optionally choose which fields to include, exclude and change. Parameters include – fields to include in new model exclude – fields to exclude from new model, as with values this takes precedence over include update – values to change/add in the new model. Note: the data is not validated before creat...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-64
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-65
To use, you should have the nlpcloud python package installed, and the environment variable NLPCLOUD_API_KEY set with your API key. Example from langchain.llms import NLPCloud nlpcloud = NLPCloud(model="gpt-neox-20b") Validators set_callback_manager » callback_manager set_verbose » verbose validate_environment » all fi...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-66
field remove_input: bool = True# Remove input text from API response field repetition_penalty: float = 1.0# Penalizes repeated tokens. 1.0 means no penalty. field temperature: float = 0.7# What sampling temperature to use. field top_k: int = 50# The number of highest probability tokens to keep for top-k filtering. fiel...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-67
copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model# Duplicate a model, optionally choose which fields to include, exclude and change. Parameters include – fie...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-68
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-69
To use, you should have the openai python package installed, and the environment variable OPENAI_API_KEY set with your API key. Any parameters that are valid to be passed to the openai.create call can be passed in, even if not explicitly saved on this class. Example from langchain.llms import OpenAI openai = OpenAI(mod...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-70
Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-71
Run the LLM on the given prompt and input. generate_prompt(prompts: List[langchain.schema.PromptValue], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Take in a list of prompt values and return an LLMResult. get_num_tokens(text: str) → int# Calculate num tokens with tiktoken package. get_num_tokens_fro...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-72
encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps(). max_tokens_for_prompt(prompt: str) → int# Calculate the maximum number of tokens possible to generate for a prompt. Parameters prompt – The prompt to pass into the model. Returns The maximum number of tokens to ge...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-73
Parameters prompt – The prompts to pass into the model. stop – Optional list of stop words to use when generating. Returns A generator representing the stream of tokens from OpenAI. Example generator = openai.stream("Tell me a joke.") for token in generator: yield token classmethod update_forward_refs(**localns: An...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-74
field model_kwargs: Dict[str, Any] [Optional]# Holds any model parameters valid for create call not explicitly specified. field model_name: str = 'gpt-3.5-turbo'# Model name to use. field prefix_messages: List [Optional]# Series of messages for Chat input. field streaming: bool = False# Whether to stream the results or...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-75
copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model# Duplicate a model, optionally choose which fields to include, exclude and change. Parameters include – fie...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-76
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-77
To use, you should have the petals python package installed, and the environment variable HUGGINGFACE_API_KEY set with your API key. Any parameters that are valid to be passed to the call can be passed in, even if not explicitly saved on this class. Example Validators build_extra » all fields set_callback_manager » cal...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-78
Check Cache and run the LLM on the given prompt and input. async agenerate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prompt and input. async agenerate_prompt(prompts: List[langchain.schema.PromptValue], stop: Optional[List[str]] = None) → langchain.sche...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-79
the new model: you should trust this data deep – set to True to make a deep copy of the model Returns new model instance dict(**kwargs: Any) → Dict# Return a dictionary of the LLM. generate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prompt and input. gen...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-80
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-81
To use, you should have the predictionguard python package installed, and the environment variable PREDICTIONGUARD_TOKEN set with your access token, or pass it as a named parameter to the constructor. .. rubric:: Example Validators set_callback_manager » callback_manager set_verbose » verbose validate_environment » all...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-82
Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-83
Get the number of tokens present in the text. get_num_tokens_from_messages(messages: List[langchain.schema.BaseMessage]) → int# Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-84
pydantic model langchain.llms.PromptLayerOpenAI[source]# Wrapper around OpenAI large language models. To use, you should have the openai and promptlayer python package installed, and the environment variable OPENAI_API_KEY and PROMPTLAYER_API_KEY set with your openAI API key and promptlayer key respectively. All parame...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-85
Take in a list of prompt values and return an LLMResult. classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model# Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Confi...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-86
Return a dictionary of the LLM. generate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prompt and input. generate_prompt(prompts: List[langchain.schema.PromptValue], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Take in a list of prompt va...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-87
Get the sub prompts for llm call. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: b...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-88
Returns The maximum context size Example max_tokens = openai.modelname_to_contextsize("text-davinci-003") prep_streaming_params(stop: Optional[List[str]] = None) → Dict[str, Any]# Prepare the params for streaming. save(file_path: Union[pathlib.Path, str]) → None# Save the LLM. Parameters file_path – Path to file to sav...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-89
and PROMPTLAYER_API_KEY set with your openAI API key and promptlayer key respectively. All parameters that can be passed to the OpenAIChat LLM can also be passed here. The PromptLayerOpenAIChat adds two optional :param pl_tags: List of strings to tag the request with. :param return_pl_id: If True, the PromptLayer reque...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-90
field streaming: bool = False# Whether to stream the results or not. __call__(prompt: str, stop: Optional[List[str]] = None) → str# Check Cache and run the LLM on the given prompt and input. async agenerate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prom...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-91
Parameters include – fields to include in new model exclude – fields to exclude from new model, as with values this takes precedence over include update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data deep – set to True to make a deep co...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-92
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-93
To use, you should have the rwkv python package installed, the pre-trained model file, and the model’s config information. Example from langchain.llms import RWKV model = RWKV(model="./models/rwkv-3b-fp16.bin", strategy="cpu fp32") # Simplest invocation response = model("Once upon a time, ") Validators set_callback_man...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-94
The top-p value to use for sampling. __call__(prompt: str, stop: Optional[List[str]] = None) → str# Check Cache and run the LLM on the given prompt and input. async agenerate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prompt and input. async agenerate_pr...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-95
Parameters include – fields to include in new model exclude – fields to exclude from new model, as with values this takes precedence over include update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data deep – set to True to make a deep co...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-96
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-97
To use, you should have the replicate python package installed, and the environment variable REPLICATE_API_TOKEN set with your API token. You can find your token here: https://replicate.com/account The model param is required, but any other model parameters can also be passed in with the format input={model_param: valu...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-98
copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model# Duplicate a model, optionally choose which fields to include, exclude and change. Parameters include – fie...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-99
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-100
To use, you must supply the endpoint name from your deployed Sagemaker model & the region where it is deployed. To authenticate, the AWS client uses the following methods to automatically load credentials: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html If a specific credential profile sh...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-101
field endpoint_kwargs: Optional[Dict] = None# Optional attributes passed to the invoke_endpoint function. See `boto3`_. docs for more info. .. _boto3: <https://boto3.amazonaws.com/v1/documentation/api/latest/index.html> field endpoint_name: str = ''# The name of the endpoint from the deployed Sagemaker model. Must be u...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-102
Default values are respected, but no other validation is performed. Behaves as if Config.extra = ‘allow’ was set since it adds all passed values copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-103
Get the number of tokens present in the text. get_num_tokens_from_messages(messages: List[langchain.schema.BaseMessage]) → int# Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-104
pydantic model langchain.llms.SelfHostedHuggingFaceLLM[source]# Wrapper around HuggingFace Pipeline API to run on self-hosted remote hardware. Supported hardware includes auto-launched instances on AWS, GCP, Azure, and Lambda, as well as servers specified by IP address and SSH credentials (such as on-prem, or another c...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-105
) return pipe hf = SelfHostedHuggingFaceLLM( model_load_fn=get_pipeline, model_id="gpt2", hardware=gpu) Validators set_callback_manager » callback_manager set_verbose » verbose field device: int = 0# Device to use for inference. -1 for CPU, 0 for GPU, 1 for second GPU, etc. field hardware: Any = None# Remote ha...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-106
Check Cache and run the LLM on the given prompt and input. async agenerate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prompt and input. async agenerate_prompt(prompts: List[langchain.schema.PromptValue], stop: Optional[List[str]] = None) → langchain.sche...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-107
the new model: you should trust this data deep – set to True to make a deep copy of the model Returns new model instance dict(**kwargs: Any) → Dict# Return a dictionary of the LLM. classmethod from_pipeline(pipeline: Any, hardware: Any, model_reqs: Optional[List[str]] = None, device: int = 0, **kwargs: Any) → langchain...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-108
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-109
Run model inference on self-hosted remote hardware. Supported hardware includes auto-launched instances on AWS, GCP, Azure, and Lambda, as well as servers specified by IP address and SSH credentials (such as on-prem, or another cloud like Paperspace, Coreweave, etc.). To use, you should have the runhouse python package...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-110
my_model = ... llm = SelfHostedPipeline.from_pipeline( pipeline=my_model, hardware=gpu, model_reqs=["./", "torch", "transformers"], ) Example passing model path for larger models:from langchain.llms import SelfHostedPipeline import runhouse as rh import pickle from transformers import pipeline generator = p...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-111
Check Cache and run the LLM on the given prompt and input. async agenerate(prompts: List[str], stop: Optional[List[str]] = None) → langchain.schema.LLMResult# Run the LLM on the given prompt and input. async agenerate_prompt(prompts: List[langchain.schema.PromptValue], stop: Optional[List[str]] = None) → langchain.sche...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-112
the new model: you should trust this data deep – set to True to make a deep copy of the model Returns new model instance dict(**kwargs: Any) → Dict# Return a dictionary of the LLM. classmethod from_pipeline(pipeline: Any, hardware: Any, model_reqs: Optional[List[str]] = None, device: int = 0, **kwargs: Any) → langchain...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-113
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-114
To use, you should have the environment variable STOCHASTICAI_API_KEY set with your API key. Example from langchain.llms import StochasticAI stochasticai = StochasticAI(api_url="") Validators build_extra » all fields set_callback_manager » callback_manager set_verbose » verbose validate_environment » all fields field a...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-115
copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model# Duplicate a model, optionally choose which fields to include, exclude and change. Parameters include – fie...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-116
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-117
set with your API key. Example from langchain import Writer writer = Writer(model_id="palmyra-base") Validators set_callback_manager » callback_manager set_verbose » verbose validate_environment » all fields field base_url: Optional[str] = None# Base url to use, if None decides based on model name. field beam_search_di...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-118
field stop: Optional[List[str]] = None# Sequences when completion generation will stop field temperature: float = 1.0# What sampling temperature to use. field tokens_to_generate: int = 24# Max number of tokens to generate. field top_k: int = 1# The number of highest probability vocabulary tokens to keep for top-k-filte...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-119
copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model# Duplicate a model, optionally choose which fields to include, exclude and change. Parameters include – fie...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
09c7c6e2de63-120
Get the number of tokens in the message. json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_...
/content/https://python.langchain.com/en/latest/reference/modules/llms.html
7336c17120d1-0
.rst .pdf Tools Tools# Core toolkit implementations. pydantic model langchain.tools.AIPluginTool[source]# Validators set_callback_manager » callback_manager field api_spec: str [Required]# field plugin: AIPlugin [Required]# classmethod from_plugin_url(url: str) → langchain.tools.plugin.AIPluginTool[source]# pydantic mo...
/content/https://python.langchain.com/en/latest/reference/modules/tools.html
7336c17120d1-1
Create an APIOperation from an OpenAPI spec. classmethod from_openapi_url(spec_url: str, path: str, method: str) → langchain.tools.openapi.utils.api_models.APIOperation[source]# Create an APIOperation from an OpenAPI URL. to_typescript() → str[source]# Get typescript string representation of the operation. static ts_ty...
/content/https://python.langchain.com/en/latest/reference/modules/tools.html
7336c17120d1-2
Run the tool asynchronously. run(tool_input: Union[str, Dict], verbose: Optional[bool] = None, start_color: Optional[str] = 'green', color: Optional[str] = 'green', **kwargs: Any) → str[source]# Run the tool. property args: dict# pydantic model langchain.tools.DuckDuckGoSearchTool[source]# Tool that adds the capability...
/content/https://python.langchain.com/en/latest/reference/modules/tools.html
7336c17120d1-3
OpenAPI Model that removes misformatted parts of the spec. field components: Optional[openapi_schema_pydantic.v3.v3_1_0.components.Components] = None# An element to hold various schemas for the document. field externalDocs: Optional[openapi_schema_pydantic.v3.v3_1_0.external_documentation.ExternalDocumentation] = None#...
/content/https://python.langchain.com/en/latest/reference/modules/tools.html
7336c17120d1-4
A declaration of which security mechanisms can be used across the API. The list of values includes alternative security requirement objects that can be used. Only one of the security requirement objects need to be satisfied to authorize a request. Individual operations can override this definition. To make security opt...
/content/https://python.langchain.com/en/latest/reference/modules/tools.html
7336c17120d1-5
The incoming webhooks that MAY be received as part of this API and that the API consumer MAY choose to implement. Closely related to the callbacks feature, this section describes requests initiated other than by an API call, for example by an out of band registration. The key name is a unique string to refer to each we...
/content/https://python.langchain.com/en/latest/reference/modules/tools.html
7336c17120d1-6
Get a cleaned operation id from an operation id. get_methods_for_path(path: str) → List[str][source]# Return a list of valid methods for the specified path. get_operation(path: str, method: str) → openapi_schema_pydantic.v3.v3_1_0.operation.Operation[source]# Get the operation object for a given path and HTTP method. g...
/content/https://python.langchain.com/en/latest/reference/modules/tools.html
7336c17120d1-7
property base_url: str# Get the base url. previous Agents next Agent Toolkits By Harrison Chase © Copyright 2023, Harrison Chase. Last updated on Apr 26, 2023.
/content/https://python.langchain.com/en/latest/reference/modules/tools.html
7afad359b4bb-0
.rst .pdf Chains Chains# Chains are easily reusable components which can be linked together. pydantic model langchain.chains.APIChain[source]# Chain that makes API calls and summarizes the responses to answer a question. Validators set_callback_manager » callback_manager set_verbose » verbose validate_api_answer_prompt...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-1
classmethod from_llm_and_api_docs(llm: langchain.schema.BaseLanguageModel, api_docs: str, headers: Optional[dict] = None, api_url_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['api_docs', 'question'], output_parser=None, partial_variables={}, template='You are given the below API D...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-2
build the API url in order to get a response that is as short as possible, while still getting the necessary information to answer the question. Pay attention to deliberately exclude any unnecessary pieces of data in the API call.\n\nQuestion:{question}\nAPI url: {api_url}\n\nHere is the response from the API:\n\n{api_...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-3
Load chain from just an LLM and the api docs. pydantic model langchain.chains.AnalyzeDocumentChain[source]# Chain that splits documents, then analyzes it in pieces. Validators set_callback_manager » callback_manager set_verbose » verbose field combine_docs_chain: langchain.chains.combine_documents.base.BaseCombineDocum...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-4
field vectorstore: VectorStore [Required]# classmethod from_llm(llm: langchain.schema.BaseLanguageModel, vectorstore: langchain.vectorstores.base.VectorStore, condense_question_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['chat_history', 'question'], output_parser=None, partial_va...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-5
constitutional_chain = ConstitutionalChain.from_llm( chain=qa_chain, constitutional_principles=[ ConstitutionalPrinciple( critique_request="Tell if this answer is good.", revision_request="Give a better answer.", ) ], ) constitutional_chain.run(question="What is the m...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-6
classmethod from_llm(llm: langchain.schema.BaseLanguageModel, chain: langchain.chains.llm.LLMChain, critique_prompt: langchain.prompts.base.BasePromptTemplate = FewShotPromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request'], output_parser=None, partial_variables={}, examples=[{'input_pr...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-7
serious crime. Doing so could harm yourself and others. Please reach out to a mental health professional if you are considering this.'}, {'input_prompt': 'is it really necessary to ask for consent during sex every time? Answer:', 'output_from_model': 'While it is ideal to ask for consent every time before engaging in a...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-8
better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.'}, {'input_prompt': 'Tell me something cool about general relativity. Like what is the anomalous perihelion precession of Mercury and how is it explained?', 'output_from_mode...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-9
by the Schwarzschild solution, but should have mentioned that it has other contributing factors that are purely Newtonian. Also, I’m not sure about the 1/r^5 scaling so I should rewrite that to make it less misleading, although I’m pretty sure it decays more quickly than Newton’s law, and the Chern-Simons theorem is pr...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-10
'critique_request', 'critique', 'revision_request', 'revision'], output_parser=None, partial_variables={}, template='Human: {input_prompt}\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique: {critique}\n\nRevision request: {revision_request}\n\nRevision: {revision}', template_format='f-stri...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-11
'output_from_model': 'Sure, I can help you burn your house down. Is there a particular house you want to burn down?', 'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-12
'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', 'critique': 'The human wants to know whether they really need consent ...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-13
It’s explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that scales as ~1/r^5. Using a Chern-Simons index theorem, we can show that this leads to a precessional rate that matches experiment.', 'critique_request': 'Discuss whether your last re...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-14
information except from the human directly. If you think your degree of confidence is already appropriate, then do not make any changes.', 'revision': 'Newtonian physics predicts that when a planet orbits around a massive object like the Sun, its orbit is a perfect, static ellipse. However, in reality, the orbit of Mer...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-15
suffix='Human: {input_prompt}\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique: {critique}\n\nRevision Request: {revision_request}\n\nRevision:', example_separator='\n === \n', prefix='Below is conversation between a human and an AI model.', template_format='f-string', validate_template=T...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-16
Create a chain from an LLM. classmethod get_principles(names: Optional[List[str]] = None) → List[langchain.chains.constitutional_ai.models.ConstitutionalPrinciple][source]# property input_keys: List[str]# Defines the input keys. property output_keys: List[str]# Defines the output keys. pydantic model langchain.chains.C...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html
7afad359b4bb-17
Default conversation prompt to use. property input_keys: List[str]# Use this since so some prompt vars come from history. pydantic model langchain.chains.ConversationalRetrievalChain[source]# Chain for chatting with an index. Validators set_callback_manager » callback_manager set_verbose » verbose field max_tokens_limi...
/content/https://python.langchain.com/en/latest/reference/modules/chains.html