langchain.llms.textgen.TextGen

class langchain.llms.textgen.TextGen(*, cache: Optional[bool] = None, verbose: bool = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, callback_manager: Optional[BaseCallbackManager] = None, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, model_url: str, preset: Optional[str] = None, max_new_tokens: Optional[int] = 250, do_sample: bool = True, temperature: Optional[float] = 1.3, top_p: Optional[float] = 0.1, typical_p: Optional[float] = 1, epsilon_cutoff: Optional[float] = 0, eta_cutoff: Optional[float] = 0, repetition_penalty: Optional[float] = 1.18, top_k: Optional[float] = 40, min_length: Optional[int] = 0, no_repeat_ngram_size: Optional[int] = 0, num_beams: Optional[int] = 1, penalty_alpha: Optional[float] = 0, length_penalty: Optional[float] = 1, early_stopping: bool = False, seed: int = - 1, add_bos_token: bool = True, truncation_length: Optional[int] = 2048, ban_eos_token: bool = False, skip_special_tokens: bool = True, stopping_strings: Optional[List[str]] = [], streaming: bool = False)

Bases: LLM

text-generation-webui models.

To use, you should have the text-generation-webui installed, a model loaded, and –api added as a command-line option.

Suggested installation, use one-click installer for your OS: https://github.com/oobabooga/text-generation-webui#one-click-installers

Parameters below taken from text-generation-webui api example: https://github.com/oobabooga/text-generation-webui/blob/main/api-examples/api-example.py

Example

from langchain.llms import TextGen
llm = TextGen(model_url="http://localhost:8500")

Create a new model by parsing and validating input data from keyword arguments.

Raises ValidationError if the input data cannot be parsed to form a valid model.

param add_bos_token: bool = True

Add the bos_token to the beginning of prompts. Disabling this can make the replies more creative.

param ban_eos_token: bool = False

Ban the eos_token. Forces the model to never end the generation prematurely.

param cache: Optional[bool] = None

param callback_manager: Optional[BaseCallbackManager] = None

param callbacks: Callbacks = None

param do_sample: bool = True

Do sample

param early_stopping: bool = False

Early stopping

param epsilon_cutoff: Optional[float] = 0

Epsilon cutoff

param eta_cutoff: Optional[float] = 0

ETA cutoff

param length_penalty: Optional[float] = 1

Length Penalty

param max_new_tokens: Optional[int] = 250

The maximum number of tokens to generate.

param metadata: Optional[Dict[str, Any]] = None

Metadata to add to the run trace.

param min_length: Optional[int] = 0

Minimum generation length in tokens.

param model_url: str [Required]

The full URL to the textgen webui including http[s]://host:port

param no_repeat_ngram_size: Optional[int] = 0

If not set to 0, specifies the length of token sets that are completely blocked from repeating at all. Higher values = blocks larger phrases, lower values = blocks words or letters from repeating. Only 0 or high values are a good idea in most cases.

param num_beams: Optional[int] = 1

Number of beams

param penalty_alpha: Optional[float] = 0

Penalty Alpha

param preset: Optional[str] = None

The preset to use in the textgen webui

param repetition_penalty: Optional[float] = 1.18

Exponential penalty factor for repeating prior tokens. 1 means no penalty, higher value = less repetition, lower value = more repetition.

param seed: int = -1

Seed (-1 for random)

param skip_special_tokens: bool = True

Skip special tokens. Some specific models need this unset.

param stopping_strings: Optional[List[str]] = []

A list of strings to stop generation when encountered.

param streaming: bool = False

Whether to stream the results, token by token (currently unimplemented).

param tags: Optional[List[str]] = None

Tags to add to the run trace.

param temperature: Optional[float] = 1.3

Primary factor to control randomness of outputs. 0 = deterministic (only the most likely token is used). Higher value = more randomness.

param top_k: Optional[float] = 40

Similar to top_p, but select instead only the top_k most likely tokens. Higher value = higher range of possible random results.

param top_p: Optional[float] = 0.1

If not set to 1, select tokens with probabilities adding up to less than this number. Higher value = higher range of possible random results.

param truncation_length: Optional[int] = 2048

Truncate the prompt up to this length. The leftmost tokens are removed if the prompt exceeds this length. Most models require this to be at most 2048.

param typical_p: Optional[float] = 1

If not set to 1, select only tokens that are at least this much more likely to appear than random tokens, given the prior text.

param verbose: bool [Optional]

Whether to print out response text.

__call__(prompt: str, stop: Optional[List[str]] = None, callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, *, tags: Optional[List[str]] = None, metadata: Optional[Dict[str, Any]] = None, **kwargs: Any) → str

Check Cache and run the LLM on the given prompt and input.

async abatch(inputs: List[Union[PromptValue, str, List[BaseMessage]]], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, max_concurrency: Optional[int] = None, **kwargs: Any) → List[str]

async agenerate(prompts: List[str], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, *, tags: Optional[Union[List[str], List[List[str]]]] = None, metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None, **kwargs: Any) → LLMResult

Run the LLM on the given prompt and input.

async agenerate_prompt(prompts: List[PromptValue], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, **kwargs: Any) → LLMResult

Asynchronously pass a sequence of prompts and return model generations.

This method should make use of batched calls for models that expose a batched API.

Use this method when you want to:

1. take advantage of batched calls,

2. need more output from the model than just the top generated value,

3. are building chains that are agnostic to the underlying language model

   type (e.g., pure text completion models vs chat models).

Parameters

• prompts – List of PromptValues. A PromptValue is an object that can be converted to match the format of any language model (string for pure text generation models and BaseMessages for chat models).

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• callbacks – Callbacks to pass through. Used for executing additional functionality, such as logging or streaming, throughout generation.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

An LLMResult, which contains a list of candidate Generations for each input

prompt and additional model provider-specific output.

async ainvoke(input: Union[PromptValue, str, List[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) → str

async apredict(text: str, *, stop: Optional[Sequence[str]] = None, **kwargs: Any) → str

Asynchronously pass a string to the model and return a string prediction.

Use this method when calling pure text generation models and only the top

candidate generation is needed.

Parameters

• text – String input to pass to the model.

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

Top model prediction as a string.

async apredict_messages(messages: List[BaseMessage], *, stop: Optional[Sequence[str]] = None, **kwargs: Any) → BaseMessage

Asynchronously pass messages to the model and return a message prediction.

Use this method when calling chat models and only the top

candidate generation is needed.

Parameters

• messages – A sequence of chat messages corresponding to a single model input.

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

Top model prediction as a message.

async astream(input: Union[PromptValue, str, List[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) → AsyncIterator[str]

batch(inputs: List[Union[PromptValue, str, List[BaseMessage]]], config: Optional[Union[RunnableConfig, List[RunnableConfig]]] = None, max_concurrency: Optional[int] = None, **kwargs: Any) → List[str]

dict(**kwargs: Any) → Dict

Return a dictionary of the LLM.

generate(prompts: List[str], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, *, tags: Optional[Union[List[str], List[List[str]]]] = None, metadata: Optional[Union[Dict[str, Any], List[Dict[str, Any]]]] = None, **kwargs: Any) → LLMResult

Run the LLM on the given prompt and input.

generate_prompt(prompts: List[PromptValue], stop: Optional[List[str]] = None, callbacks: Union[List[BaseCallbackHandler], BaseCallbackManager, None, List[Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]]] = None, **kwargs: Any) → LLMResult

Pass a sequence of prompts to the model and return model generations.

This method should make use of batched calls for models that expose a batched API.

Use this method when you want to:

1. take advantage of batched calls,

2. need more output from the model than just the top generated value,

3. are building chains that are agnostic to the underlying language model

   type (e.g., pure text completion models vs chat models).

Parameters

• prompts – List of PromptValues. A PromptValue is an object that can be converted to match the format of any language model (string for pure text generation models and BaseMessages for chat models).

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• callbacks – Callbacks to pass through. Used for executing additional functionality, such as logging or streaming, throughout generation.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

An LLMResult, which contains a list of candidate Generations for each input

prompt and additional model provider-specific output.

get_num_tokens(text: str) → int

Get the number of tokens present in the text.

Useful for checking if an input will fit in a model’s context window.

Parameters

text – The string input to tokenize.

Returns

The integer number of tokens in the text.

get_num_tokens_from_messages(messages: List[BaseMessage]) → int

Get the number of tokens in the messages.

Useful for checking if an input will fit in a model’s context window.

Parameters

messages – The message inputs to tokenize.

Returns

The sum of the number of tokens across the messages.

get_token_ids(text: str) → List[int]

Return the ordered ids of the tokens in a text.

Parameters

text – The string input to tokenize.

Returns

A list of ids corresponding to the tokens in the text, in order they occur

in the text.

invoke(input: Union[PromptValue, str, List[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) → str

predict(text: str, *, stop: Optional[Sequence[str]] = None, **kwargs: Any) → str

Pass a single string input to the model and return a string prediction.

Use this method when passing in raw text. If you want to pass in specific

types of chat messages, use predict_messages.

Parameters

• text – String input to pass to the model.

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

Top model prediction as a string.

predict_messages(messages: List[BaseMessage], *, stop: Optional[Sequence[str]] = None, **kwargs: Any) → BaseMessage

Pass a message sequence to the model and return a message prediction.

Use this method when passing in chat messages. If you want to pass in raw text,

use predict.

Parameters

• messages – A sequence of chat messages corresponding to a single model input.

• stop – Stop words to use when generating. Model output is cut off at the first occurrence of any of these substrings.

• **kwargs – Arbitrary additional keyword arguments. These are usually passed to the model provider API call.

Returns

Top model prediction as a message.

validator raise_deprecation  »  all fields

Raise deprecation warning if callback_manager is used.

save(file_path: Union[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”)

validator set_verbose  »  verbose

If verbose is None, set it.

This allows users to pass in None as verbose to access the global setting.

stream(input: Union[PromptValue, str, List[BaseMessage]], config: Optional[RunnableConfig] = None, *, stop: Optional[List[str]] = None, **kwargs: Any) → Iterator[str]

to_json() → Union[SerializedConstructor, SerializedNotImplemented]

to_json_not_implemented() → SerializedNotImplemented

property lc_attributes: Dict

Return a list of attribute names that should be included in the serialized kwargs. These attributes must be accepted by the constructor.

property lc_namespace: List[str]

Return the namespace of the langchain object. eg. [“langchain”, “llms”, “openai”]

property lc_secrets: Dict[str, str]

Return a map of constructor argument names to secret ids. eg. {“openai_api_key”: “OPENAI_API_KEY”}

property lc_serializable: bool

Return whether or not the class is serializable.

model Config

Bases: object

Configuration for this pydantic object.

arbitrary_types_allowed = True

Examples using TextGen

• TextGen