llama_ros.langchain.llama_ros.LlamaROS Class Reference

Inheritance diagram for llama_ros.langchain.llama_ros.LlamaROS:

Collaboration diagram for llama_ros.langchain.llama_ros.LlamaROS:

Public Member Functions
int	get_num_tokens (self, str text)
Public Member Functions inherited from llama_ros.langchain.llama_ros_common.LlamaROSCommon
Dict	validate_environment (cls, Dict values)
None	cancel (self)

Protected Member Functions
Dict[str, Any]	_default_params (self)
str	_llm_type (self)
str	_call (self, str prompt, Optional[List[str]] stop=None, Optional[CallbackManagerForLLMRun] run_manager=None, **Any kwargs)
Iterator[GenerationChunk]	_stream (self, str prompt, Optional[List[str]] stop=None, Optional[CallbackManagerForLLMRun] run_manager=None, **Any kwargs)
Protected Member Functions inherited from llama_ros.langchain.llama_ros_common.LlamaROSCommon
GenerateResponse.Result	_create_action_goal (self, str prompt, Optional[List[str]] stop=None, Optional[str] image_url=None, Optional[np.ndarray] image=None, Optional[str] tools_grammar=None, **kwargs)

Additional Inherited Members
Static Public Attributes inherited from llama_ros.langchain.llama_ros_common.LlamaROSCommon
LlamaClientNode	llama_client = None
CvBridge	cv_bridge = CvBridge()
Metadata	model_metadata = None
int	n_prev = 64
int	n_probs = 1
int	min_keep = 0
bool	ignore_eos = False
dict	logit_bias = {}
float	temp = 0.80
float	dynatemp_range = 0.0
float	dynatemp_exponent = 1.0
int	top_k = 40
float	top_p = 0.95
float	min_p = 0.05
float	xtc_probability = 0.0
float	xtc_threshold = 0.1
float	typical_p = 1.00
int	penalty_last_n = 64
float	penalty_repeat = 1.00
float	penalty_freq = 0.00
float	penalty_present = 0.00
float	dry_multiplier = 0.0
float	dry_base = 1.75
int	dry_allowed_length = 2
int	dry_penalty_last_n = -1
list	dry_sequence_breakers = ["\\n", ":", '\\"', "*"]
int	mirostat = 0
float	mirostat_eta = 0.10
float	mirostat_tau = 5.0
str	samplers_sequence = "edkypmxt"
str	grammar = ""
str	grammar_schema = ""
list	penalty_prompt_tokens = []
bool	use_penalty_prompt_tokens = False

Member Function Documentation

_call()

str llama_ros.langchain.llama_ros.LlamaROS._call ( self, str prompt, Optional[List[str]] stop = None, Optional[CallbackManagerForLLMRun] run_manager = None, **Any kwargs )

protected

_default_params()

Dict[str, Any] llama_ros.langchain.llama_ros.LlamaROS._default_params ( self )

protected

_llm_type()

str llama_ros.langchain.llama_ros.LlamaROS._llm_type ( self )

protected

_stream()

Iterator[GenerationChunk] llama_ros.langchain.llama_ros.LlamaROS._stream ( self, str prompt, Optional[List[str]] stop = None, Optional[CallbackManagerForLLMRun] run_manager = None, **Any kwargs )

protected

get_num_tokens()

int llama_ros.langchain.llama_ros.LlamaROS.get_num_tokens	(		self,
		str	text )

---

The documentation for this class was generated from the following file:

• llama_ros/llama_ros/langchain/llama_ros.py