langchain/libs/experimental/langchain_experimental/synthetic_data/__init__.py
Bagatur 8e0d5813c2
langchain[patch], experimental[patch]: replace langchain.schema imports (#15410)
Import from core instead.

Ran:
```bash
git grep -l 'from langchain.schema\.output_parser' | xargs -L 1 sed -i '' "s/from\ langchain\.schema\.output_parser/from\ langchain_core.output_parsers/g"
git grep -l 'from langchain.schema\.messages' | xargs -L 1 sed -i '' "s/from\ langchain\.schema\.messages/from\ langchain_core.messages/g"
git grep -l 'from langchain.schema\.document' | xargs -L 1 sed -i '' "s/from\ langchain\.schema\.document/from\ langchain_core.documents/g"
git grep -l 'from langchain.schema\.runnable' | xargs -L 1 sed -i '' "s/from\ langchain\.schema\.runnable/from\ langchain_core.runnables/g"
git grep -l 'from langchain.schema\.vectorstore' | xargs -L 1 sed -i '' "s/from\ langchain\.schema\.vectorstore/from\ langchain_core.vectorstores/g"
git grep -l 'from langchain.schema\.language_model' | xargs -L 1 sed -i '' "s/from\ langchain\.schema\.language_model/from\ langchain_core.language_models/g"
git grep -l 'from langchain.schema\.embeddings' | xargs -L 1 sed -i '' "s/from\ langchain\.schema\.embeddings/from\ langchain_core.embeddings/g"
git grep -l 'from langchain.schema\.storage' | xargs -L 1 sed -i '' "s/from\ langchain\.schema\.storage/from\ langchain_core.stores/g"
git checkout master libs/langchain/tests/unit_tests/schema/
make format
cd libs/experimental
make format
cd ../langchain
make format
```
2024-01-02 15:09:45 -05:00

50 lines
1.5 KiB
Python

from typing import Any, Dict, List, Optional
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
from langchain.prompts import PromptTemplate
from langchain_core.language_models import BaseLanguageModel
from langchain_experimental.synthetic_data.prompts import SENTENCE_PROMPT
def create_data_generation_chain(
llm: BaseLanguageModel,
prompt: Optional[PromptTemplate] = None,
) -> Chain:
"""Creates a chain that generates synthetic sentences with
provided fields.
Args:
llm: The language model to use.
prompt: Prompt to feed the language model with.
If not provided, the default one will be used.
"""
prompt = prompt or SENTENCE_PROMPT
return LLMChain(
llm=llm,
prompt=prompt,
)
class DatasetGenerator:
"""Generates synthetic dataset with a given language model."""
def __init__(
self,
llm: BaseLanguageModel,
sentence_preferences: Optional[Dict[str, Any]] = None,
):
self.generator = create_data_generation_chain(llm)
self.sentence_preferences = sentence_preferences or {}
def __call__(self, fields_collection: List[List[Any]]) -> List[Dict[str, Any]]:
results: List[Dict[str, Any]] = []
for fields in fields_collection:
results.append(
self.generator(
{"fields": fields, "preferences": self.sentence_preferences}
)
)
return results