mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-05 04:55:14 +00:00
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)
Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
This commit is contained in:
Bagatur
GitHub
232
libs/community/langchain_community/llms/deepsparse.py
Normal file
232
libs/community/langchain_community/llms/deepsparse.py
Normal file
@@ -0,0 +1,232 @@
|
||||
# flake8: noqa
|
||||
from typing import Any, AsyncIterator, Dict, Iterator, List, Optional, Union
|
||||
from langchain_core.pydantic_v1 import root_validator
|
||||
from langchain_core.callbacks import (
|
||||
AsyncCallbackManagerForLLMRun,
|
||||
CallbackManagerForLLMRun,
|
||||
)
|
||||
from langchain_core.language_models.llms import LLM
|
||||
from langchain_community.llms.utils import enforce_stop_tokens
|
||||
from langchain_core.outputs import GenerationChunk
|
||||
|
||||
|
||||
class DeepSparse(LLM):
|
||||
"""Neural Magic DeepSparse LLM interface.
|
||||
To use, you should have the ``deepsparse`` or ``deepsparse-nightly``
|
||||
python package installed. See https://github.com/neuralmagic/deepsparse
|
||||
This interface let's you deploy optimized LLMs straight from the
|
||||
[SparseZoo](https://sparsezoo.neuralmagic.com/?useCase=text_generation)
|
||||
Example:
|
||||
.. code-block:: python
|
||||
from langchain_community.llms import DeepSparse
|
||||
llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
|
||||
""" # noqa: E501
|
||||
|
||||
pipeline: Any #: :meta private:
|
||||
|
||||
model: str
|
||||
"""The path to a model file or directory or the name of a SparseZoo model stub."""
|
||||
|
||||
model_config: Optional[Dict[str, Any]] = None
|
||||
"""Keyword arguments passed to the pipeline construction.
|
||||
Common parameters are sequence_length, prompt_sequence_length"""
|
||||
|
||||
generation_config: Union[None, str, Dict] = None
|
||||
"""GenerationConfig dictionary consisting of parameters used to control
|
||||
sequences generated for each prompt. Common parameters are:
|
||||
max_length, max_new_tokens, num_return_sequences, output_scores,
|
||||
top_p, top_k, repetition_penalty."""
|
||||
|
||||
streaming: bool = False
|
||||
"""Whether to stream the results, token by token."""
|
||||
|
||||
@property
|
||||
def _identifying_params(self) -> Dict[str, Any]:
|
||||
"""Get the identifying parameters."""
|
||||
return {
|
||||
"model": self.model,
|
||||
"model_config": self.model_config,
|
||||
"generation_config": self.generation_config,
|
||||
"streaming": self.streaming,
|
||||
}
|
||||
|
||||
@property
|
||||
def _llm_type(self) -> str:
|
||||
"""Return type of llm."""
|
||||
return "deepsparse"
|
||||
|
||||
@root_validator()
|
||||
def validate_environment(cls, values: Dict) -> Dict:
|
||||
"""Validate that ``deepsparse`` package is installed."""
|
||||
try:
|
||||
from deepsparse import Pipeline
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"Could not import `deepsparse` package. "
|
||||
"Please install it with `pip install deepsparse`"
|
||||
)
|
||||
|
||||
model_config = values["model_config"] or {}
|
||||
|
||||
values["pipeline"] = Pipeline.create(
|
||||
task="text_generation",
|
||||
model_path=values["model"],
|
||||
**model_config,
|
||||
)
|
||||
return values
|
||||
|
||||
def _call(
|
||||
self,
|
||||
prompt: str,
|
||||
stop: Optional[List[str]] = None,
|
||||
run_manager: Optional[CallbackManagerForLLMRun] = None,
|
||||
**kwargs: Any,
|
||||
) -> str:
|
||||
"""Generate text from a prompt.
|
||||
Args:
|
||||
prompt: The prompt to generate text from.
|
||||
stop: A list of strings to stop generation when encountered.
|
||||
Returns:
|
||||
The generated text.
|
||||
Example:
|
||||
.. code-block:: python
|
||||
from langchain_community.llms import DeepSparse
|
||||
llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
|
||||
llm("Tell me a joke.")
|
||||
"""
|
||||
if self.streaming:
|
||||
combined_output = ""
|
||||
for chunk in self._stream(
|
||||
prompt=prompt, stop=stop, run_manager=run_manager, **kwargs
|
||||
):
|
||||
combined_output += chunk.text
|
||||
text = combined_output
|
||||
else:
|
||||
text = (
|
||||
self.pipeline(
|
||||
sequences=prompt, generation_config=self.generation_config
|
||||
)
|
||||
.generations[0]
|
||||
.text
|
||||
)
|
||||
|
||||
if stop is not None:
|
||||
text = enforce_stop_tokens(text, stop)
|
||||
|
||||
return text
|
||||
|
||||
async def _acall(
|
||||
self,
|
||||
prompt: str,
|
||||
stop: Optional[List[str]] = None,
|
||||
run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
|
||||
**kwargs: Any,
|
||||
) -> str:
|
||||
"""Generate text from a prompt.
|
||||
Args:
|
||||
prompt: The prompt to generate text from.
|
||||
stop: A list of strings to stop generation when encountered.
|
||||
Returns:
|
||||
The generated text.
|
||||
Example:
|
||||
.. code-block:: python
|
||||
from langchain_community.llms import DeepSparse
|
||||
llm = DeepSparse(model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none")
|
||||
llm("Tell me a joke.")
|
||||
"""
|
||||
if self.streaming:
|
||||
combined_output = ""
|
||||
async for chunk in self._astream(
|
||||
prompt=prompt, stop=stop, run_manager=run_manager, **kwargs
|
||||
):
|
||||
combined_output += chunk.text
|
||||
text = combined_output
|
||||
else:
|
||||
text = (
|
||||
self.pipeline(
|
||||
sequences=prompt, generation_config=self.generation_config
|
||||
)
|
||||
.generations[0]
|
||||
.text
|
||||
)
|
||||
|
||||
if stop is not None:
|
||||
text = enforce_stop_tokens(text, stop)
|
||||
|
||||
return text
|
||||
|
||||
def _stream(
|
||||
self,
|
||||
prompt: str,
|
||||
stop: Optional[List[str]] = None,
|
||||
run_manager: Optional[CallbackManagerForLLMRun] = None,
|
||||
**kwargs: Any,
|
||||
) -> Iterator[GenerationChunk]:
|
||||
"""Yields results objects as they are generated in real time.
|
||||
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 prompt to pass into the model.
|
||||
stop: Optional list of stop words to use when generating.
|
||||
Returns:
|
||||
A generator representing the stream of tokens being generated.
|
||||
Yields:
|
||||
A dictionary like object containing a string token.
|
||||
Example:
|
||||
.. code-block:: python
|
||||
from langchain_community.llms import DeepSparse
|
||||
llm = DeepSparse(
|
||||
model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none",
|
||||
streaming=True
|
||||
)
|
||||
for chunk in llm.stream("Tell me a joke",
|
||||
stop=["'","\n"]):
|
||||
print(chunk, end='', flush=True)
|
||||
"""
|
||||
inference = self.pipeline(
|
||||
sequences=prompt, generation_config=self.generation_config, streaming=True
|
||||
)
|
||||
for token in inference:
|
||||
chunk = GenerationChunk(text=token.generations[0].text)
|
||||
yield chunk
|
||||
|
||||
if run_manager:
|
||||
run_manager.on_llm_new_token(token=chunk.text)
|
||||
|
||||
async def _astream(
|
||||
self,
|
||||
prompt: str,
|
||||
stop: Optional[List[str]] = None,
|
||||
run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
|
||||
**kwargs: Any,
|
||||
) -> AsyncIterator[GenerationChunk]:
|
||||
"""Yields results objects as they are generated in real time.
|
||||
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 prompt to pass into the model.
|
||||
stop: Optional list of stop words to use when generating.
|
||||
Returns:
|
||||
A generator representing the stream of tokens being generated.
|
||||
Yields:
|
||||
A dictionary like object containing a string token.
|
||||
Example:
|
||||
.. code-block:: python
|
||||
from langchain_community.llms import DeepSparse
|
||||
llm = DeepSparse(
|
||||
model="zoo:nlg/text_generation/codegen_mono-350m/pytorch/huggingface/bigpython_bigquery_thepile/base_quant-none",
|
||||
streaming=True
|
||||
)
|
||||
for chunk in llm.stream("Tell me a joke",
|
||||
stop=["'","\n"]):
|
||||
print(chunk, end='', flush=True)
|
||||
"""
|
||||
inference = self.pipeline(
|
||||
sequences=prompt, generation_config=self.generation_config, streaming=True
|
||||
)
|
||||
for token in inference:
|
||||
chunk = GenerationChunk(text=token.generations[0].text)
|
||||
yield chunk
|
||||
|
||||
if run_manager:
|
||||
await run_manager.on_llm_new_token(token=chunk.text)
|
||||
Reference in New Issue
Block a user