github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-02 03:26:17 +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

52
libs/partners/pinecone/langchain_pinecone/embeddings.py
View File

@@ -1,16 +1,19 @@
import logging
from typing import Dict, Iterable, List, Optional
from typing import Any, Dict, Iterable, List, Optional
import aiohttp
from langchain_core.embeddings import Embeddings
from langchain_core.pydantic_v1 import (
BaseModel,
Field,
SecretStr,
root_validator,
)
from langchain_core.utils import secret_from_env
from pinecone import Pinecone as PineconeClient # type: ignore
from pinecone import Pinecone as PineconeClient # type: ignore[import-untyped]
from pydantic import (
BaseModel,
ConfigDict,
Field,
PrivateAttr,
SecretStr,
model_validator,
)
from typing_extensions import Self
logger = logging.getLogger(__name__)
@@ -29,8 +32,8 @@ class PineconeEmbeddings(BaseModel, Embeddings):
"""
# Clients
_client: PineconeClient = Field(default=None, exclude=True)
_async_client: aiohttp.ClientSession = Field(default=None, exclude=True)
_client: PineconeClient = PrivateAttr(default=None)
_async_client: aiohttp.ClientSession = PrivateAttr(default=None)
model: str
"""Model to use for example 'multilingual-e5-large'."""
# Config
@@ -44,7 +47,7 @@ class PineconeEmbeddings(BaseModel, Embeddings):
dimension: Optional[int] = None
#
show_progress_bar: bool = False
pinecone_api_key: Optional[SecretStr] = Field(
pinecone_api_key: SecretStr = Field(
default_factory=secret_from_env(
"PINECONE_API_KEY",
error_message="Pinecone API key not found. Please set the PINECONE_API_KEY "
@@ -56,12 +59,15 @@ class PineconeEmbeddings(BaseModel, Embeddings):
If not provided, will look for the PINECONE_API_KEY environment variable."""
class Config:
extra = "forbid"
allow_population_by_field_name = True
model_config = ConfigDict(
extra="forbid",
populate_by_name=True,
protected_namespaces=(),
)
@root_validator(pre=True)
def set_default_config(cls, values: dict) -> dict:
@model_validator(mode="before")
@classmethod
def set_default_config(cls, values: dict) -> Any:
"""Set default configuration based on model."""
default_config_map = {
"multilingual-e5-large": {
@@ -79,23 +85,23 @@ class PineconeEmbeddings(BaseModel, Embeddings):
values[key] = value
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 Pinecone version and credentials exist in environment."""
api_key_str = values["pinecone_api_key"].get_secret_value()
api_key_str = self.pinecone_api_key.get_secret_value()
client = PineconeClient(api_key=api_key_str, source_tag="langchain")
values["_client"] = client
self._client = client
# initialize async client
if not values.get("_async_client"):
values["_async_client"] = aiohttp.ClientSession(
if not self._async_client:
self._async_client = aiohttp.ClientSession(
headers={
"Api-Key": api_key_str,
"Content-Type": "application/json",
"X-Pinecone-API-Version": "2024-07",
}
)
return values
return self
def _get_batch_iterator(self, texts: List[str]) -> Iterable:
if self.batch_size is None: