added custom llm and embeddings instance

Author: raphael-intugle

src/intugle/core/llms/chat.py

@@ -1,6 +1,6 @@
 import logging
 
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Optional
 
 from langchain.chat_models import init_chat_model
 from langchain.output_parsers import (
@@ -30,7 +30,7 @@ class ChatModelLLM:
 
     def __init__(
         self,
-        model_name: str,
+        model_name: Optional[str] = None,
         response_schemas: list[ResponseSchema] = None,
         output_parser=StructuredOutputParser,
         prompt_template=ChatPromptTemplate,
@@ -39,9 +39,14 @@ def __init__(
         *args,
         **kwargs,
     ):
-        self.model: BaseChatModel = init_chat_model(
-            model_name, max_retries=self.MAX_RETRIES, rate_limiter=self._get_rate_limiter(), **config
-        )  # llm model
+        if settings.CUSTOM_LLM_INSTANCE:
+            self.model: "BaseChatModel" = settings.CUSTOM_LLM_INSTANCE
+        elif model_name:
+            self.model: "BaseChatModel" = init_chat_model(
+                model_name, max_retries=self.MAX_RETRIES, rate_limiter=self._get_rate_limiter(), **config
+            )
+        else:
+            raise ValueError("Either 'settings.CUSTOM_LLM_INSTANCE' must be set or 'LLM_PROVIDER' must be provided.")
 
         self.parser: StructuredOutputParser = output_parser  # the output parser
 
@@ -135,6 +140,8 @@ def invoke(self, *args, **kwargs):
 
     @classmethod
     def get_llm(cls, model_name: str, llm_config: dict = {}):
+        if settings.CUSTOM_LLM_INSTANCE:
+            return settings.CUSTOM_LLM_INSTANCE
         return init_chat_model(
             model_name, max_retries=cls.MAX_RETRIES, rate_limiter=cls._get_rate_limiter(), **llm_config
         )

src/intugle/core/llms/embeddings.py

@@ -8,6 +8,8 @@
 
 from langchain.embeddings.base import init_embeddings
 
+from intugle.core import settings
+
 
 class EmbeddingsType(str, Enum):
     DENSE = "dense"
@@ -30,7 +32,10 @@ def __init__(
         embeddings_size: Optional[int] = None,
     ):
         self.model_name = model_name
-        self.model = init_embeddings(model_name, **config)
+        if settings.CUSTOM_EMBEDDINGS_INSTANCE:
+            self.model = settings.CUSTOM_EMBEDDINGS_INSTANCE
+        else:
+            self.model = init_embeddings(model_name, **config)
         self._embed_func: Dict[EmbeddingsType, Callable] = {
             EmbeddingsType.DENSE: self.dense,
             EmbeddingsType.SPARSE: self.sparse,

src/intugle/core/settings.py

@@ -4,7 +4,7 @@
 
 from functools import lru_cache
 from pathlib import Path
-from typing import Optional
+from typing import Any, Optional
 
 from dotenv import load_dotenv
 from pydantic_settings import BaseSettings, SettingsConfigDict
@@ -66,6 +66,8 @@ class Settings(BaseSettings):
     MAX_RETRIES: int = 5
     SLEEP_TIME: int = 25
     ENABLE_RATE_LIMITER: bool = False
+    CUSTOM_LLM_INSTANCE: Optional[Any] = None
+    CUSTOM_EMBEDDINGS_INSTANCE: Optional[Any] = None
 
     # LP
     HALLUCINATIONS_MAX_RETRY: int = 2