github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-02 19:47:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

multiple: pydantic 2 compatibility, v0.3 (#26443)

Browse Source 
Signed-off-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Dan O'Donovan <dan.odonovan@gmail.com>
Co-authored-by: Tom Daniel Grande <tomdgrande@gmail.com>
Co-authored-by: Grande <Tom.Daniel.Grande@statsbygg.no>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Tomaz Bratanic <bratanic.tomaz@gmail.com>
Co-authored-by: ZhangShenao <15201440436@163.com>
Co-authored-by: Friso H. Kingma <fhkingma@gmail.com>
Co-authored-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Nuno Campos <nuno@langchain.dev>
Co-authored-by: Morgante Pell <morgantep@google.com>
This commit is contained in:
Erick Friis
2024-09-13 14:38:45 -07:00
committed by GitHub
parent d9813bdbbc
commit c2a3021bb0
1402 changed files with 38318 additions and 30410 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
libs/partners/huggingface/langchain_huggingface/llms/huggingface_endpoint.py
View File

@@ -9,8 +9,9 @@ from langchain_core.callbacks import (
)
from langchain_core.language_models.llms import LLM
from langchain_core.outputs import GenerationChunk
from langchain_core.pydantic_v1 import Field, root_validator
from langchain_core.utils import get_from_dict_or_env, get_pydantic_field_names
from langchain_core.utils import from_env, get_pydantic_field_names
from pydantic import ConfigDict, Field, model_validator
from typing_extensions import Self
logger = logging.getLogger(__name__)
@@ -71,7 +72,9 @@ class HuggingFaceEndpoint(LLM):
should be pass as env variable in `HF_INFERENCE_ENDPOINT`"""
repo_id: Optional[str] = None
"""Repo to use. If endpoint_url is not specified then this needs to given"""
huggingfacehub_api_token: Optional[str] = None
huggingfacehub_api_token: Optional[str] = Field(
default_factory=from_env("HUGGINGFACEHUB_API_TOKEN", default=None)
)
max_new_tokens: int = 512
"""Maximum number of generated tokens"""
top_k: Optional[int] = None
@@ -112,19 +115,19 @@ class HuggingFaceEndpoint(LLM):
model_kwargs: Dict[str, Any] = Field(default_factory=dict)
"""Holds any model parameters valid for `call` not explicitly specified"""
model: str
client: Any
async_client: Any
client: Any = None #: :meta private:
async_client: Any = None #: :meta private:
task: Optional[str] = None
"""Task to call the model with.
Should be a task that returns `generated_text` or `summary_text`."""
class Config:
"""Configuration for this pydantic object."""
model_config = ConfigDict(
extra="forbid",
)
extra = "forbid"
@root_validator(pre=True)
def build_extra(cls, values: Dict[str, Any]) -> Dict[str, Any]:
@model_validator(mode="before")
@classmethod
def build_extra(cls, values: Dict[str, Any]) -> Any:
"""Build extra kwargs from additional params that were passed in."""
all_required_field_names = get_pydantic_field_names(cls)
extra = values.get("model_kwargs", {})
@@ -182,8 +185,8 @@ class HuggingFaceEndpoint(LLM):
)
return values
@root_validator(pre=False, skip_on_failure=True)
def validate_environment(cls, values: Dict) -> Dict:
@model_validator(mode="after")
def validate_environment(self) -> Self:
"""Validate that package is installed and that the API token is valid."""
try:
from huggingface_hub import login # type: ignore[import]
@@ -194,12 +197,8 @@ class HuggingFaceEndpoint(LLM):
"Please install it with `pip install huggingface_hub`."
)
values["huggingfacehub_api_token"] = get_from_dict_or_env(
values, "huggingfacehub_api_token", "HUGGINGFACEHUB_API_TOKEN", None
)
huggingfacehub_api_token = get_from_dict_or_env(
values, "huggingfacehub_api_token", "HF_TOKEN", None
huggingfacehub_api_token = self.huggingfacehub_api_token or os.getenv(
"HF_TOKEN"
)
if huggingfacehub_api_token is not None:
@@ -213,20 +212,20 @@ class HuggingFaceEndpoint(LLM):
from huggingface_hub import AsyncInferenceClient, InferenceClient
values["client"] = InferenceClient(
model=values["model"],
timeout=values["timeout"],
self.client = InferenceClient(
model=self.model,
timeout=self.timeout,
token=huggingfacehub_api_token,
**values["server_kwargs"],
**self.server_kwargs,
)
values["async_client"] = AsyncInferenceClient(
model=values["model"],
timeout=values["timeout"],
self.async_client = AsyncInferenceClient(
model=self.model,
timeout=self.timeout,
token=huggingfacehub_api_token,
**values["server_kwargs"],
**self.server_kwargs,
)
return values
return self
@property
def _default_params(self) -> Dict[str, Any]:

10
libs/partners/huggingface/langchain_huggingface/llms/huggingface_pipeline.py
View File

@@ -7,6 +7,7 @@ from typing import Any, Iterator, List, Mapping, Optional
from langchain_core.callbacks import CallbackManagerForLLMRun
from langchain_core.language_models.llms import BaseLLM
from langchain_core.outputs import Generation, GenerationChunk, LLMResult
from pydantic import ConfigDict
DEFAULT_MODEL_ID = "gpt2"
DEFAULT_TASK = "text-generation"
@@ -53,7 +54,7 @@ class HuggingFacePipeline(BaseLLM):
hf = HuggingFacePipeline(pipeline=pipe)
"""
pipeline: Any #: :meta private:
pipeline: Any = None #: :meta private:
model_id: str = DEFAULT_MODEL_ID
"""Model name to use."""
model_kwargs: Optional[dict] = None
@@ -63,10 +64,9 @@ class HuggingFacePipeline(BaseLLM):
batch_size: int = DEFAULT_BATCH_SIZE
"""Batch size to use when passing multiple documents to generate."""
class Config:
"""Configuration for this pydantic object."""
extra = "forbid"
model_config = ConfigDict(
extra="forbid",
)
@classmethod
def from_model_id(