remove CVEs (#8092)

This PR aims to move all code with CVEs into `langchain.experimental`.
Note that we are NOT yet removing from the core `langchain` package - we
will give people a week to migrate here.

See MIGRATE.md for how to migrate

Zero changes to functionality

Vulnerabilities this addresses:

PALChain:
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5752409
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5759265

SQLDatabaseChain
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5759268

`load_prompt` (Python files only)
- https://security.snyk.io/vuln/SNYK-PYTHON-LANGCHAIN-5725807

libs/experimental/langchain_experimental/llms/rellm_decoder.py

@@ -1,67 +0,0 @@
-"""Experimental implementation of RELLM wrapped LLM."""
-from __future__ import annotations
-
-from typing import TYPE_CHECKING, Any, List, Optional, cast
-
-from langchain.callbacks.manager import CallbackManagerForLLMRun
-from langchain.llms.huggingface_pipeline import HuggingFacePipeline
-from langchain.llms.utils import enforce_stop_tokens
-from pydantic import Field, root_validator
-
-if TYPE_CHECKING:
-    import rellm
-    from regex import Pattern as RegexPattern
-else:
-    try:
-        from regex import Pattern as RegexPattern
-    except ImportError:
-        pass
-
-
-def import_rellm() -> rellm:
-    """Lazily import rellm."""
-    try:
-        import rellm
-    except ImportError:
-        raise ValueError(
-            "Could not import rellm python package. "
-            "Please install it with `pip install rellm`."
-        )
-    return rellm
-
-
-class RELLM(HuggingFacePipeline):
-    regex: RegexPattern = Field(..., description="The structured format to complete.")
-    max_new_tokens: int = Field(
-        default=200, description="Maximum number of new tokens to generate."
-    )
-
-    @root_validator
-    def check_rellm_installation(cls, values: dict) -> dict:
-        import_rellm()
-        return values
-
-    def _call(
-        self,
-        prompt: str,
-        stop: Optional[List[str]] = None,
-        run_manager: Optional[CallbackManagerForLLMRun] = None,
-        **kwargs: Any,
-    ) -> str:
-        rellm = import_rellm()
-        from transformers import Text2TextGenerationPipeline
-
-        pipeline = cast(Text2TextGenerationPipeline, self.pipeline)
-
-        text = rellm.complete_re(
-            prompt,
-            self.regex,
-            tokenizer=pipeline.tokenizer,
-            model=pipeline.model,
-            max_new_tokens=self.max_new_tokens,
-        )
-        if stop is not None:
-            # This is a bit hacky, but I can't figure out a better way to enforce
-            # stop tokens when making calls to huggingface_hub.
-            text = enforce_stop_tokens(text, stop)
-        return text