github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-16 15:04:13 +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

67
libs/partners/openai/langchain_openai/embeddings/azure.py
View File

@@ -2,11 +2,12 @@
from __future__ import annotations
from typing import Callable, Dict, Optional, Union
from typing import Callable, Optional, Union
import openai
from langchain_core.pydantic_v1 import Field, SecretStr, root_validator
from langchain_core.utils import from_env, secret_from_env
from pydantic import Field, SecretStr, model_validator
from typing_extensions import Self, cast
from langchain_openai.embeddings.base import OpenAIEmbeddings
@@ -154,21 +155,21 @@ class AzureOpenAIEmbeddings(OpenAIEmbeddings):
chunk_size: int = 2048
"""Maximum number of texts to embed in each batch"""
@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 api key and python package exists in environment."""
# For backwards compatibility. Before openai v1, no distinction was made
# between azure_endpoint and base_url (openai_api_base).
openai_api_base = values["openai_api_base"]
if openai_api_base and values["validate_base_url"]:
openai_api_base = self.openai_api_base
if openai_api_base and self.validate_base_url:
if "/openai" not in openai_api_base:
values["openai_api_base"] += "/openai"
self.openai_api_base = cast(str, self.openai_api_base) + "/openai"
raise ValueError(
"As of openai>=1.0.0, Azure endpoints should be specified via "
"the `azure_endpoint` param not `openai_api_base` "
"(or alias `base_url`). "
)
if values["deployment"]:
if self.deployment:
raise ValueError(
"As of openai>=1.0.0, if `deployment` (or alias "
"`azure_deployment`) is specified then "
@@ -176,39 +177,37 @@ class AzureOpenAIEmbeddings(OpenAIEmbeddings):
"Instead use `deployment` (or alias `azure_deployment`) "
"and `azure_endpoint`."
)
client_params = {
"api_version": values["openai_api_version"],
"azure_endpoint": values["azure_endpoint"],
"azure_deployment": values["deployment"],
client_params: dict = {
"api_version": self.openai_api_version,
"azure_endpoint": self.azure_endpoint,
"azure_deployment": self.deployment,
"api_key": (
values["openai_api_key"].get_secret_value()
if values["openai_api_key"]
else None
self.openai_api_key.get_secret_value() if self.openai_api_key else None
),
"azure_ad_token": (
values["azure_ad_token"].get_secret_value()
if values["azure_ad_token"]
else None
self.azure_ad_token.get_secret_value() if self.azure_ad_token else None
),
"azure_ad_token_provider": values["azure_ad_token_provider"],
"organization": values["openai_organization"],
"base_url": values["openai_api_base"],
"timeout": values["request_timeout"],
"max_retries": values["max_retries"],
"default_headers": values["default_headers"],
"default_query": values["default_query"],
"azure_ad_token_provider": self.azure_ad_token_provider,
"organization": self.openai_organization,
"base_url": self.openai_api_base,
"timeout": self.request_timeout,
"max_retries": self.max_retries,
"default_headers": self.default_headers,
"default_query": self.default_query,
}
if not values.get("client"):
sync_specific = {"http_client": values["http_client"]}
values["client"] = openai.AzureOpenAI(
**client_params, **sync_specific
if not self.client:
sync_specific: dict = {"http_client": self.http_client}
self.client = openai.AzureOpenAI(
**client_params, # type: ignore[arg-type]
**sync_specific,
).embeddings
if not values.get("async_client"):
async_specific = {"http_client": values["http_async_client"]}
values["async_client"] = openai.AsyncAzureOpenAI(
**client_params, **async_specific
if not self.async_client:
async_specific: dict = {"http_client": self.http_async_client}
self.async_client = openai.AsyncAzureOpenAI(
**client_params, # type: ignore[arg-type]
**async_specific,
).embeddings
return values
return self
@property
def _llm_type(self) -> str:

79
libs/partners/openai/langchain_openai/embeddings/base.py
View File

@@ -20,8 +20,9 @@ from typing import (
import openai
import tiktoken
from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import BaseModel, Field, SecretStr, root_validator
from langchain_core.utils import from_env, get_pydantic_field_names, secret_from_env
from pydantic import BaseModel, ConfigDict, Field, SecretStr, model_validator
from typing_extensions import Self
logger = logging.getLogger(__name__)
@@ -263,14 +264,13 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
"""Whether to check the token length of inputs and automatically split inputs
longer than embedding_ctx_length."""
class Config:
"""Configuration for this pydantic object."""
model_config = ConfigDict(
extra="forbid", populate_by_name=True, protected_namespaces=()
)
extra = "forbid"
allow_population_by_field_name = True
@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", {})
@@ -295,41 +295,37 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
values["model_kwargs"] = extra
return values
@root_validator(pre=False, skip_on_failure=True, allow_reuse=True)
def validate_environment(cls, values: Dict) -> Dict:
@model_validator(mode="after")
def validate_environment(self) -> Self:
"""Validate that api key and python package exists in environment."""
if values["openai_api_type"] in ("azure", "azure_ad", "azuread"):
if self.openai_api_type in ("azure", "azure_ad", "azuread"):
raise ValueError(
"If you are using Azure, "
"please use the `AzureOpenAIEmbeddings` class."
)
client_params = {
client_params: dict = {
"api_key": (
values["openai_api_key"].get_secret_value()
if values["openai_api_key"]
else None
self.openai_api_key.get_secret_value() if self.openai_api_key else None
),
"organization": values["openai_organization"],
"base_url": values["openai_api_base"],
"timeout": values["request_timeout"],
"max_retries": values["max_retries"],
"default_headers": values["default_headers"],
"default_query": values["default_query"],
"organization": self.openai_organization,
"base_url": self.openai_api_base,
"timeout": self.request_timeout,
"max_retries": self.max_retries,
"default_headers": self.default_headers,
"default_query": self.default_query,
}
if values["openai_proxy"] and (
values["http_client"] or values["http_async_client"]
):
openai_proxy = values["openai_proxy"]
http_client = values["http_client"]
http_async_client = values["http_async_client"]
if self.openai_proxy and (self.http_client or self.http_async_client):
openai_proxy = self.openai_proxy
http_client = self.http_client
http_async_client = self.http_async_client
raise ValueError(
"Cannot specify 'openai_proxy' if one of "
"'http_client'/'http_async_client' is already specified. Received:\n"
f"{openai_proxy=}\n{http_client=}\n{http_async_client=}"
)
if not values.get("client"):
if values["openai_proxy"] and not values["http_client"]:
if not self.client:
if self.openai_proxy and not self.http_client:
try:
import httpx
except ImportError as e:
@@ -337,13 +333,11 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
"Could not import httpx python package. "
"Please install it with `pip install httpx`."
) from e
values["http_client"] = httpx.Client(proxy=values["openai_proxy"])
sync_specific = {"http_client": values["http_client"]}
values["client"] = openai.OpenAI(
**client_params, **sync_specific
).embeddings
if not values.get("async_client"):
if values["openai_proxy"] and not values["http_async_client"]:
self.http_client = httpx.Client(proxy=self.openai_proxy)
sync_specific = {"http_client": self.http_client}
self.client = openai.OpenAI(**client_params, **sync_specific).embeddings # type: ignore[arg-type]
if not self.async_client:
if self.openai_proxy and not self.http_async_client:
try:
import httpx
except ImportError as e:
@@ -351,14 +345,13 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
"Could not import httpx python package. "
"Please install it with `pip install httpx`."
) from e
values["http_async_client"] = httpx.AsyncClient(
proxy=values["openai_proxy"]
)
async_specific = {"http_client": values["http_async_client"]}
values["async_client"] = openai.AsyncOpenAI(
**client_params, **async_specific
self.http_async_client = httpx.AsyncClient(proxy=self.openai_proxy)
async_specific = {"http_client": self.http_async_client}
self.async_client = openai.AsyncOpenAI(
**client_params,
**async_specific, # type: ignore[arg-type]
).embeddings
return values
return self
@property
def _invocation_params(self) -> Dict[str, Any]: