refactor: Migrate from BaseLanguageModel to field_typing.LanguageModel

src/backend/base/langflow/components/agents/CSVAgent.py

@@ -1,7 +1,7 @@
 from langchain_experimental.agents.agent_toolkits.csv.base import create_csv_agent
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import AgentExecutor, BaseLanguageModel
+from langflow.field_typing import AgentExecutor, LanguageModel
 
 
 class CSVAgentComponent(CustomComponent):
@@ -11,7 +11,7 @@ class CSVAgentComponent(CustomComponent):
 
     def build_config(self):
         return {
-            "llm": {"display_name": "LLM", "type": BaseLanguageModel},
+            "llm": {"display_name": "LLM", "type": LanguageModel},
             "path": {"display_name": "Path", "field_type": "file", "suffixes": [".csv"], "file_types": [".csv"]},
             "handle_parsing_errors": {"display_name": "Handle Parse Errors", "advanced": True},
             "agent_type": {
@@ -22,7 +22,7 @@ class CSVAgentComponent(CustomComponent):
         }
 
     def build(
-        self, llm: BaseLanguageModel, path: str, handle_parsing_errors: bool = True, agent_type: str = "openai-tools"
+        self, llm: LanguageModel, path: str, handle_parsing_errors: bool = True, agent_type: str = "openai-tools"
     ) -> AgentExecutor:
         # Instantiate and return the CSV agent class with the provided llm and path
         return create_csv_agent(

src/backend/base/langflow/components/agents/JsonAgent.py

@@ -3,7 +3,7 @@ from langchain_community.agent_toolkits import create_json_agent
 from langchain_community.agent_toolkits.json.toolkit import JsonToolkit
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class JsonAgentComponent(CustomComponent):
@@ -18,7 +18,7 @@ class JsonAgentComponent(CustomComponent):
 
     def build(
         self,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         toolkit: JsonToolkit,
     ) -> AgentExecutor:
         return create_json_agent(llm=llm, toolkit=toolkit)

src/backend/base/langflow/components/agents/SQLAgent.py

@@ -6,7 +6,7 @@ from langchain_community.agent_toolkits.sql.base import create_sql_agent
 from langchain_community.utilities import SQLDatabase
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class SQLAgentComponent(CustomComponent):
@@ -22,7 +22,7 @@ class SQLAgentComponent(CustomComponent):
 
     def build(
         self,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         database_uri: str,
         verbose: bool = False,
     ) -> Union[AgentExecutor, Callable]:

src/backend/base/langflow/components/agents/ToolCallingAgent.py

@@ -4,7 +4,7 @@ from langchain.agents.tool_calling_agent.base import create_tool_calling_agent
 from langchain_core.prompts import ChatPromptTemplate
 
 from langflow.base.agents.agent import LCAgentComponent
-from langflow.field_typing import BaseLanguageModel, Text, Tool
+from langflow.field_typing import LanguageModel, Text, Tool
 from langflow.schema import Data
 
 
@@ -39,7 +39,7 @@ class ToolCallingAgentComponent(LCAgentComponent):
     async def build(
         self,
         input_value: str,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         tools: List[Tool],
         user_prompt: str = "{input}",
         message_history: Optional[List[Data]] = None,

src/backend/base/langflow/components/agents/VectorStoreAgent.py

@@ -4,7 +4,7 @@ from langchain.agents import AgentExecutor, create_vectorstore_agent
 from langchain.agents.agent_toolkits.vectorstore.toolkit import VectorStoreToolkit
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class VectorStoreAgentComponent(CustomComponent):
@@ -19,7 +19,7 @@ class VectorStoreAgentComponent(CustomComponent):
 
     def build(
         self,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         vector_store_toolkit: VectorStoreToolkit,
     ) -> Union[AgentExecutor, Callable]:
         return create_vectorstore_agent(llm=llm, toolkit=vector_store_toolkit)

src/backend/base/langflow/components/agents/VectorStoreRouterAgent.py

@@ -2,7 +2,7 @@ from typing import Callable
 
 from langchain.agents import create_vectorstore_router_agent
 from langchain.agents.agent_toolkits.vectorstore.toolkit import VectorStoreRouterToolkit
-from langchain_core.language_models.base import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 from langflow.custom import CustomComponent
 
@@ -17,5 +17,5 @@ class VectorStoreRouterAgentComponent(CustomComponent):
             "vectorstoreroutertoolkit": {"display_name": "Vector Store Router Toolkit"},
         }
 
-    def build(self, llm: BaseLanguageModel, vectorstoreroutertoolkit: VectorStoreRouterToolkit) -> Callable:
+    def build(self, llm: LanguageModel, vectorstoreroutertoolkit: VectorStoreRouterToolkit) -> Callable:
         return create_vectorstore_router_agent(llm=llm, toolkit=vectorstoreroutertoolkit)

src/backend/base/langflow/components/agents/XMLAgent.py

@@ -4,7 +4,7 @@ from langchain.agents import create_xml_agent
 from langchain_core.prompts import ChatPromptTemplate
 
 from langflow.base.agents.agent import LCAgentComponent
-from langflow.field_typing import BaseLanguageModel, Text, Tool
+from langflow.field_typing import LanguageModel, Text, Tool
 from langflow.schema import Data
 
 
@@ -72,7 +72,7 @@ class XMLAgentComponent(LCAgentComponent):
     async def build(
         self,
         input_value: str,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         tools: List[Tool],
         user_prompt: str = "{input}",
         system_message: str = "You are a helpful assistant",

src/backend/base/langflow/components/chains/ConversationChain.py

@@ -3,7 +3,7 @@ from typing import Optional
 from langchain.chains import ConversationChain
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, BaseMemory, Text
+from langflow.field_typing import BaseMemory, LanguageModel, Text
 
 
 class ConversationChainComponent(CustomComponent):
@@ -27,7 +27,7 @@ class ConversationChainComponent(CustomComponent):
     def build(
         self,
         input_value: Text,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         memory: Optional[BaseMemory] = None,
     ) -> Text:
         if memory is None:

src/backend/base/langflow/components/chains/LLMChain.py

@@ -4,7 +4,7 @@ from langchain.chains.llm import LLMChain
 from langchain_core.prompts import PromptTemplate
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, BaseMemory, Text
+from langflow.field_typing import BaseMemory, LanguageModel, Text
 
 
 class LLMChainComponent(CustomComponent):
@@ -21,7 +21,7 @@ class LLMChainComponent(CustomComponent):
     def build(
         self,
         template: Text,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         memory: Optional[BaseMemory] = None,
     ) -> Text:
         prompt = PromptTemplate.from_template(template)

src/backend/base/langflow/components/chains/LLMCheckerChain.py

@@ -1,7 +1,7 @@
 from langchain.chains import LLMCheckerChain
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 
 
 class LLMCheckerChainComponent(CustomComponent):
@@ -21,7 +21,7 @@ class LLMCheckerChainComponent(CustomComponent):
     def build(
         self,
         input_value: Text,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
     ) -> Text:
         chain = LLMCheckerChain.from_llm(llm=llm)
         response = chain.invoke({chain.input_key: input_value})

src/backend/base/langflow/components/chains/LLMMathChain.py

@@ -3,7 +3,7 @@ from typing import Optional
 from langchain.chains import LLMChain, LLMMathChain
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, BaseMemory, Text
+from langflow.field_typing import BaseMemory, LanguageModel, Text
 
 
 class LLMMathChainComponent(CustomComponent):
@@ -27,7 +27,7 @@ class LLMMathChainComponent(CustomComponent):
     def build(
         self,
         input_value: Text,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         llm_chain: LLMChain,
         input_key: str = "question",
         output_key: str = "answer",

src/backend/base/langflow/components/chains/RetrievalQA.py

@@ -4,7 +4,7 @@ from langchain.chains.retrieval_qa.base import RetrievalQA
 from langchain_core.documents import Document
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, BaseMemory, BaseRetriever, Text
+from langflow.field_typing import BaseMemory, BaseRetriever, LanguageModel, Text
 from langflow.schema import Data
 
 
@@ -29,7 +29,7 @@ class RetrievalQAComponent(CustomComponent):
 
     def build(
         self,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         chain_type: str,
         retriever: BaseRetriever,
         input_value: str = "",

src/backend/base/langflow/components/chains/RetrievalQAWithSourcesChain.py

@@ -4,7 +4,7 @@ from langchain.chains import RetrievalQAWithSourcesChain
 from langchain_core.documents import Document
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, BaseMemory, BaseRetriever, Text
+from langflow.field_typing import BaseMemory, BaseRetriever, LanguageModel, Text
 
 
 class RetrievalQAWithSourcesChainComponent(CustomComponent):
@@ -32,7 +32,7 @@ class RetrievalQAWithSourcesChainComponent(CustomComponent):
         self,
         input_value: Text,
         retriever: BaseRetriever,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         chain_type: str,
         memory: Optional[BaseMemory] = None,
         return_source_documents: Optional[bool] = True,

src/backend/base/langflow/components/chains/SQLGenerator.py

@@ -6,7 +6,7 @@ from langchain_core.prompts import PromptTemplate
 from langchain_core.runnables import Runnable
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 
 
 class SQLGeneratorComponent(CustomComponent):
@@ -35,7 +35,7 @@ class SQLGeneratorComponent(CustomComponent):
         self,
         input_value: Text,
         db: SQLDatabase,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         top_k: int = 5,
         prompt: Optional[Text] = None,
     ) -> Text:

src/backend/base/langflow/components/experimental/AgentComponent.py

@@ -5,7 +5,7 @@ from langchain_core.prompts.chat import HumanMessagePromptTemplate, SystemMessag
 
 from langflow.base.agents.agent import LCAgentComponent
 from langflow.base.agents.utils import AGENTS, AgentSpec, get_agents_list
-from langflow.field_typing import BaseLanguageModel, Text, Tool
+from langflow.field_typing import LanguageModel, Text, Tool
 from langflow.schema import Data
 from langflow.schema.dotdict import dotdict
 
@@ -145,7 +145,7 @@ class AgentComponent(LCAgentComponent):
         self,
         agent_name: str,
         input_value: str,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         tools: List[Tool],
         system_message: str = "You are a helpful assistant. Help the user answer any questions.",
         user_prompt: str = "{input}",

src/backend/base/langflow/components/helpers/ShouldRunNext.py

@@ -2,14 +2,14 @@ from langchain_core.messages import BaseMessage
 from langchain_core.prompts import PromptTemplate
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 
 
 class ShouldRunNextComponent(CustomComponent):
     display_name = "Should Run Next"
     description = "Determines if a vertex is runnable."
 
-    def build(self, llm: BaseLanguageModel, question: str, context: str, retries: int = 3) -> Text:
+    def build(self, llm: LanguageModel, question: str, context: str, retries: int = 3) -> Text:
         template = "Given the following question and the context below, answer with a yes or no.\n\n{error_message}\n\nQuestion: {question}\n\nContext: {context}\n\nAnswer:"
 
         prompt = PromptTemplate.from_template(template)

src/backend/base/langflow/components/model_specs/AmazonBedrockSpecs.py

@@ -3,7 +3,7 @@ from typing import Optional
 from langchain_community.llms.bedrock import Bedrock
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class AmazonBedrockComponent(CustomComponent):
@@ -46,7 +46,7 @@ class AmazonBedrockComponent(CustomComponent):
         endpoint_url: Optional[str] = None,
         streaming: bool = False,
         cache: Optional[bool] = None,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         try:
             output = Bedrock(
                 credentials_profile_name=credentials_profile_name,

src/backend/base/langflow/components/model_specs/AnthropicLLMSpecs.py

@@ -1,10 +1,10 @@
 from typing import Optional
 
 from langchain_anthropic import ChatAnthropic
-from langchain_core.language_models import BaseLanguageModel
 from pydantic.v1 import SecretStr
 
 from langflow.custom import CustomComponent
+from langflow.field_typing import LanguageModel
 
 
 class ChatAntropicSpecsComponent(CustomComponent):
@@ -57,7 +57,7 @@ class ChatAntropicSpecsComponent(CustomComponent):
         max_tokens: Optional[int] = 1000,
         temperature: Optional[float] = None,
         api_endpoint: Optional[str] = None,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         # Set default API endpoint if not provided
         if not api_endpoint:
             api_endpoint = "https://api.anthropic.com"

src/backend/base/langflow/components/model_specs/AzureChatOpenAISpecs.py

@@ -1,10 +1,10 @@
 from typing import Optional
 
-from langchain_core.language_models import BaseLanguageModel
 from langchain_openai import AzureChatOpenAI
 from pydantic.v1 import SecretStr
 
 from langflow.custom import CustomComponent
+from langflow.field_typing import LanguageModel
 
 
 class AzureChatOpenAISpecsComponent(CustomComponent):
@@ -81,7 +81,7 @@ class AzureChatOpenAISpecsComponent(CustomComponent):
         api_version: str,
         temperature: float = 0.7,
         max_tokens: Optional[int] = 1000,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         if api_key:
             azure_api_key = SecretStr(api_key)
         else:

src/backend/base/langflow/components/model_specs/BaiduQianfanChatEndpointsSpecs.py

@@ -1,11 +1,10 @@
 from typing import Optional
 
 from langchain_community.chat_models.baidu_qianfan_endpoint import QianfanChatEndpoint
-
 from pydantic.v1 import SecretStr
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class QianfanChatEndpointComponent(CustomComponent):
@@ -80,7 +79,7 @@ class QianfanChatEndpointComponent(CustomComponent):
         temperature: Optional[float] = None,
         penalty_score: Optional[float] = None,
         endpoint: Optional[str] = None,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         try:
             output = QianfanChatEndpoint(  # type: ignore
                 model=model,

src/backend/base/langflow/components/model_specs/BaiduQianfanLLMEndpointsSpecs.py

@@ -3,7 +3,7 @@ from typing import Optional
 from langchain_community.llms.baidu_qianfan_endpoint import QianfanLLMEndpoint
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class QianfanLLMEndpointComponent(CustomComponent):
@@ -78,7 +78,7 @@ class QianfanLLMEndpointComponent(CustomComponent):
         temperature: Optional[float] = None,
         penalty_score: Optional[float] = None,
         endpoint: Optional[str] = None,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         try:
             output = QianfanLLMEndpoint(  # type: ignore
                 model=model,

src/backend/base/langflow/components/model_specs/ChatAnthropicSpecs.py

@@ -3,9 +3,7 @@ from typing import Optional
 from langchain_anthropic import ChatAnthropic
 from pydantic.v1.types import SecretStr
 
-
-from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class AnthropicLLM(CustomComponent):
@@ -69,7 +67,7 @@ class AnthropicLLM(CustomComponent):
         max_tokens: Optional[int] = 1000,
         temperature: Optional[float] = None,
         anthropic_api_url: Optional[str] = None,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         # Set default API endpoint if not provided
         if not anthropic_api_url:
             anthropic_api_url = "https://api.anthropic.com"

src/backend/base/langflow/components/model_specs/ChatLiteLLMSpecs.py

@@ -3,7 +3,7 @@ from typing import Any, Dict, Optional
 from langchain_community.chat_models.litellm import ChatLiteLLM, ChatLiteLLMException
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class ChatLiteLLMComponent(CustomComponent):
@@ -116,7 +116,7 @@ class ChatLiteLLMComponent(CustomComponent):
         max_tokens: int = 256,
         max_retries: int = 6,
         verbose: bool = False,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         try:
             import litellm  # type: ignore
 

src/backend/base/langflow/components/model_specs/ChatMistralSpecs.py

@@ -4,7 +4,7 @@ from langchain_mistralai import ChatMistralAI
 from pydantic.v1 import SecretStr
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class MistralAIModelComponent(CustomComponent):
@@ -68,7 +68,7 @@ class MistralAIModelComponent(CustomComponent):
         mistral_api_key: Optional[str] = None,
         max_tokens: Optional[int] = None,
         mistral_api_base: Optional[str] = None,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         # Set default API endpoint if not provided
         if not mistral_api_base:
             mistral_api_base = "https://api.mistral.ai"

src/backend/base/langflow/components/model_specs/ChatOpenAISpecs.py

@@ -5,7 +5,7 @@ from pydantic.v1 import SecretStr
 
 from langflow.base.models.openai_constants import MODEL_NAMES
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, NestedDict
+from langflow.field_typing import LanguageModel, NestedDict
 
 
 class ChatOpenAIComponent(CustomComponent):
@@ -57,7 +57,7 @@ class ChatOpenAIComponent(CustomComponent):
         openai_api_base: Optional[str] = None,
         openai_api_key: Optional[str] = None,
         temperature: float = 0.7,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         if not openai_api_base:
             openai_api_base = "https://api.openai.com/v1"
         if openai_api_key:

src/backend/base/langflow/components/model_specs/ChatVertexAISpecs.py

@@ -1,8 +1,10 @@
 from typing import Optional
 
 from langchain_community.chat_models.vertexai import ChatVertexAI
+
+
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class ChatVertexAIComponent(CustomComponent):
@@ -70,7 +72,7 @@ class ChatVertexAIComponent(CustomComponent):
         top_k: int = 40,
         top_p: float = 0.95,
         verbose: bool = False,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         return ChatVertexAI(
             credentials=credentials,
             location=location,

src/backend/base/langflow/components/model_specs/CohereSpecs.py

@@ -1,7 +1,7 @@
 from typing import Optional
 
 from langchain_cohere import ChatCohere
-from langchain_core.language_models.base import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 from pydantic.v1 import SecretStr
 
 from langflow.custom import CustomComponent
@@ -29,7 +29,7 @@ class CohereComponent(CustomComponent):
         cohere_api_key: str,
         max_tokens: Optional[int] = 256,
         temperature: float = 0.75,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         if cohere_api_key:
             api_key = SecretStr(cohere_api_key)
         else:

src/backend/base/langflow/components/model_specs/GoogleGenerativeAISpecs.py

@@ -4,7 +4,7 @@ from langchain_google_genai import ChatGoogleGenerativeAI  # type: ignore
 from pydantic.v1.types import SecretStr
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, RangeSpec
+from langflow.field_typing import LanguageModel, RangeSpec
 
 
 class GoogleGenerativeAIComponent(CustomComponent):
@@ -62,7 +62,7 @@ class GoogleGenerativeAIComponent(CustomComponent):
         top_k: Optional[int] = None,
         top_p: Optional[float] = None,
         n: Optional[int] = 1,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         return ChatGoogleGenerativeAI(
             model=model,
             max_output_tokens=max_output_tokens or None,  # type: ignore

src/backend/base/langflow/components/model_specs/GroqModelSpecs.py

@@ -6,7 +6,7 @@ from pydantic.v1 import SecretStr
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.groq_constants import MODEL_NAMES
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class GroqModelSpecs(LCModelComponent):
@@ -74,7 +74,7 @@ class GroqModelSpecs(LCModelComponent):
         temperature: float = 0.1,
         n: Optional[int] = 1,
         stream: bool = False,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         return ChatGroq(
             model_name=model_name,
             max_tokens=max_tokens or None,  # type: ignore

src/backend/base/langflow/components/model_specs/HuggingFaceEndpointsSpecs.py

@@ -3,7 +3,7 @@ from typing import Optional
 from langchain_community.llms.huggingface_endpoint import HuggingFaceEndpoint
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class HuggingFaceEndpointsComponent(CustomComponent):
@@ -32,7 +32,7 @@ class HuggingFaceEndpointsComponent(CustomComponent):
         task: str = "text2text-generation",
         huggingfacehub_api_token: Optional[str] = None,
         model_kwargs: Optional[dict] = None,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         try:
             output = HuggingFaceEndpoint(  # type: ignore
                 endpoint_url=endpoint_url,

src/backend/base/langflow/components/model_specs/OllamaLLMSpecs.py

@@ -3,7 +3,7 @@ from typing import List, Optional
 from langchain_community.llms.ollama import Ollama
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class OllamaLLM(CustomComponent):
@@ -118,7 +118,7 @@ class OllamaLLM(CustomComponent):
         tfs_z: Optional[float] = None,
         top_k: Optional[int] = None,
         top_p: Optional[int] = None,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         if not base_url:
             base_url = "http://localhost:11434"
 

src/backend/base/langflow/components/model_specs/VertexAISpecs.py

@@ -1,8 +1,10 @@
 from typing import Dict, Optional
 
 from langchain_community.llms.vertexai import VertexAI
+
+
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class VertexAIComponent(CustomComponent):
@@ -128,7 +130,7 @@ class VertexAIComponent(CustomComponent):
         top_p: float = 0.95,
         tuned_model_name: Optional[str] = None,
         verbose: bool = False,
-    ) -> BaseLanguageModel:
+    ) -> LanguageModel:
         return VertexAI(
             credentials=credentials,
             location=location,

src/backend/base/langflow/components/models/AmazonBedrockModel.py

@@ -2,7 +2,7 @@ from langchain_aws import ChatBedrock
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.io import BoolInput, DictInput, DropdownInput, MessageInput, Output, StrInput
 
 
@@ -78,7 +78,7 @@ class AmazonBedrockComponent(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         model_id = self.model_id
         credentials_profile_name = self.credentials_profile_name
         region_name = self.region_name

src/backend/base/langflow/components/models/AnthropicModel.py

@@ -3,7 +3,7 @@ from pydantic.v1 import SecretStr
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.io import BoolInput, DropdownInput, FloatInput, IntInput, Output, SecretStrInput, TextInput
 
 
@@ -82,7 +82,7 @@ class AnthropicModelComponent(LCModelComponent):
         self.status = result.content
         return prefill + result.content
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         model = self.model
         anthropic_api_key = self.anthropic_api_key
         max_tokens = self.max_tokens

src/backend/base/langflow/components/models/AzureOpenAIModel.py

@@ -3,8 +3,8 @@ from pydantic.v1 import SecretStr
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
-from langflow.io import BoolInput, DropdownInput, FloatInput, IntInput, MessageInput, Output, StrInput, SecretStrInput
+from langflow.field_typing import LanguageModel, Text
+from langflow.io import BoolInput, DropdownInput, FloatInput, IntInput, MessageInput, Output, SecretStrInput, StrInput
 
 
 class AzureChatOpenAIComponent(LCModelComponent):
@@ -87,7 +87,7 @@ class AzureChatOpenAIComponent(LCModelComponent):
         self.status = result
         return result
 
-    def model_response(self) -> BaseLanguageModel:
+    def model_response(self) -> LanguageModel:
         model = self.model
         azure_endpoint = self.azure_endpoint
         azure_deployment = self.azure_deployment

src/backend/base/langflow/components/models/BaiduQianfanChatModel.py

@@ -3,8 +3,8 @@ from pydantic.v1 import SecretStr
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
-from langflow.io import BoolInput, FloatInput, Output, SecretStrInput, TextInput, DropdownInput
+from langflow.io import BoolInput, DropdownInput, FloatInput, Output, SecretStrInput, TextInput
+from langflow.io import BoolInput, DropdownInput, FloatInput, Output, SecretStrInput, TextInput
 
 
 class QianfanChatEndpointComponent(LCModelComponent):
@@ -98,7 +98,7 @@ class QianfanChatEndpointComponent(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         model = self.model
         qianfan_ak = self.qianfan_ak
         qianfan_sk = self.qianfan_sk

src/backend/base/langflow/components/models/ChatLiteLLMModel.py

@@ -1,9 +1,10 @@
 from typing import Optional
 
 from langchain_community.chat_models.litellm import ChatLiteLLM, ChatLiteLLMException
+
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 from langflow.io import (
     BoolInput,
     DictInput,
@@ -137,7 +138,7 @@ class ChatLiteLLMModelComponent(LCModelComponent):
         self.status = message
         return message
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         try:
             import litellm  # type: ignore
 

src/backend/base/langflow/components/models/CohereModel.py

@@ -4,7 +4,7 @@ from pydantic.v1 import SecretStr
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.io import BoolInput, FloatInput, MessageInput, Output, SecretStrInput, StrInput
 
 
@@ -46,7 +46,7 @@ class CohereComponent(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel | BaseChatModel:
+    def build_model(self) -> LanguageModel | BaseChatModel:
         cohere_api_key = self.cohere_api_key
         temperature = self.temperature
 

src/backend/base/langflow/components/models/GoogleGenerativeAIModel.py

@@ -2,7 +2,7 @@ from pydantic.v1 import SecretStr
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.io import BoolInput, DropdownInput, FloatInput, IntInput, MessageInput, Output, SecretStrInput, StrInput
 
 
@@ -82,7 +82,7 @@ class GoogleGenerativeAIComponent(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         try:
             from langchain_google_genai import ChatGoogleGenerativeAI
         except ImportError:

src/backend/base/langflow/components/models/GroqModel.py

@@ -4,7 +4,7 @@ from pydantic.v1 import SecretStr
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.groq_constants import MODEL_NAMES
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.io import BoolInput, DropdownInput, FloatInput, IntInput, Output, SecretStrInput, TextInput
 
 
@@ -82,7 +82,7 @@ class GroqModel(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         groq_api_key = self.groq_api_key
         model_name = self.model_name
         max_tokens = self.max_tokens

src/backend/base/langflow/components/models/HuggingFaceModel.py

@@ -3,7 +3,7 @@ from langchain_community.llms.huggingface_endpoint import HuggingFaceEndpoint
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.io import BoolInput, DictInput, DropdownInput, MessageInput, Output, SecretStrInput, StrInput
 
 
@@ -45,7 +45,7 @@ class HuggingFaceEndpointsComponent(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         endpoint_url = self.endpoint_url
         task = self.task
         huggingfacehub_api_token = self.huggingfacehub_api_token

src/backend/base/langflow/components/models/MistralModel.py

@@ -3,7 +3,7 @@ from pydantic.v1 import SecretStr
 
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.io import BoolInput, DropdownInput, FloatInput, IntInput, MessageInput, Output, SecretStrInput, StrInput
 
 
@@ -79,7 +79,7 @@ class MistralAIModelComponent(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         mistral_api_key = self.mistral_api_key
         temperature = self.temperature
         model_name = self.model_name

src/backend/base/langflow/components/models/OllamaModel.py

@@ -2,7 +2,7 @@ from langchain_community.chat_models import ChatOllama
 from langchain_core.language_models.chat_models import BaseChatModel
 
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, Output, StrInput
 
 
@@ -177,7 +177,7 @@ class ChatOllamaComponent(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel | BaseChatModel:
+    def build_model(self) -> LanguageModel | BaseChatModel:
         # Mapping mirostat settings to their corresponding values
         mirostat_options = {"Mirostat": 1, "Mirostat 2.0": 2}
 

src/backend/base/langflow/components/models/OpenAIModel.py

@@ -7,7 +7,7 @@ from pydantic.v1 import SecretStr
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
 from langflow.base.models.openai_constants import MODEL_NAMES
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 from langflow.inputs import (
     BoolInput,
     DictInput,
@@ -89,7 +89,7 @@ class OpenAIModelComponent(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         # self.output_schea is a list of dictionaries
         # let's convert it to a dictionary
         output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})

src/backend/base/langflow/components/models/VertexAiModel.py

@@ -1,7 +1,9 @@
 from langchain_google_vertexai import ChatVertexAI
+
+
 from langflow.base.constants import STREAM_INFO_TEXT
 from langflow.base.models.model import LCModelComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.io import BoolInput, FileInput, FloatInput, IntInput, MessageInput, MultilineInput, Output, StrInput
 
 
@@ -60,7 +62,7 @@ class ChatVertexAIComponent(LCModelComponent):
         self.status = result
         return result
 
-    def build_model(self) -> BaseLanguageModel:
+    def build_model(self) -> LanguageModel:
         credentials = self.credentials
         location = self.location
         max_output_tokens = self.max_output_tokens

src/backend/base/langflow/components/retrievers/MultiQueryRetriever.py

@@ -3,7 +3,7 @@ from typing import Optional
 from langchain.retrievers import MultiQueryRetriever
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, BaseRetriever, PromptTemplate, Text
+from langflow.field_typing import BaseRetriever, LanguageModel, PromptTemplate, Text
 
 
 class MultiQueryRetrieverComponent(CustomComponent):
@@ -39,7 +39,7 @@ class MultiQueryRetrieverComponent(CustomComponent):
 
     def build(
         self,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         retriever: BaseRetriever,
         prompt: Optional[Text] = None,
         parser_key: str = "lines",

src/backend/base/langflow/components/retrievers/SelfQueryRetriever.py

@@ -4,7 +4,7 @@ from langchain.retrievers.self_query.base import SelfQueryRetriever
 from langchain_core.vectorstores import VectorStore
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, Text
+from langflow.field_typing import LanguageModel, Text
 from langflow.schema import Data
 from langflow.schema.message import Message
 
@@ -45,7 +45,7 @@ class SelfQueryRetrieverComponent(CustomComponent):
         vectorstore: VectorStore,
         attribute_infos: list[Data],
         document_content_description: Text,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
     ) -> Data:
         metadata_field_infos = [AttributeInfo(**value.data) for value in attribute_infos]
         self_query_retriever = SelfQueryRetriever.from_llm(

src/backend/base/langflow/components/retrievers/VectaraSelfQueryRetriver.py

@@ -3,11 +3,11 @@ from typing import List
 
 from langchain.chains.query_constructor.base import AttributeInfo
 from langchain.retrievers.self_query.base import SelfQueryRetriever
-from langchain_core.language_models import BaseLanguageModel
 from langchain_core.retrievers import BaseRetriever
 from langchain_core.vectorstores import VectorStore
 
 from langflow.custom import CustomComponent
+from langflow.field_typing.constants import LanguageModel
 
 
 class VectaraSelfQueryRetriverComponent(CustomComponent):
@@ -38,7 +38,7 @@ class VectaraSelfQueryRetriverComponent(CustomComponent):
         self,
         vectorstore: VectorStore,
         document_content_description: str,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
         metadata_field_info: List[str],
     ) -> BaseRetriever:
         metadata_field_obj = []

src/backend/base/langflow/components/toolkits/OpenAPIToolkit.py

@@ -6,7 +6,7 @@ from langchain_community.tools.json.tool import JsonSpec
 from langchain_community.utilities.requests import TextRequestsWrapper
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel
+from langflow.field_typing import LanguageModel
 
 
 class OpenAPIToolkitComponent(CustomComponent):
@@ -19,7 +19,7 @@ class OpenAPIToolkitComponent(CustomComponent):
             "requests_wrapper": {"display_name": "Text Requests Wrapper"},
         }
 
-    def build(self, llm: BaseLanguageModel, path: str, allow_dangerous_requests: bool = False) -> BaseToolkit:
+    def build(self, llm: LanguageModel, path: str, allow_dangerous_requests: bool = False) -> BaseToolkit:
         if path.endswith("yaml") or path.endswith("yml"):
             yaml_dict = yaml.load(open(path, "r"), Loader=yaml.FullLoader)
             spec = JsonSpec(dict_=yaml_dict)

src/backend/base/langflow/components/toolkits/VectorStoreRouterToolkit.py

@@ -3,7 +3,7 @@ from typing import List, Union
 from langchain.agents.agent_toolkits.vectorstore.toolkit import VectorStoreInfo, VectorStoreRouterToolkit
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, Tool
+from langflow.field_typing import LanguageModel, Tool
 
 
 class VectorStoreRouterToolkitComponent(CustomComponent):
@@ -16,9 +16,7 @@ class VectorStoreRouterToolkitComponent(CustomComponent):
             "llm": {"display_name": "LLM"},
         }
 
-    def build(
-        self, vectorstores: List[VectorStoreInfo], llm: BaseLanguageModel
-    ) -> Union[Tool, VectorStoreRouterToolkit]:
+    def build(self, vectorstores: List[VectorStoreInfo], llm: LanguageModel) -> Union[Tool, VectorStoreRouterToolkit]:
         print("vectorstores", vectorstores)
         print("llm", llm)
         return VectorStoreRouterToolkit(vectorstores=vectorstores, llm=llm)

src/backend/base/langflow/components/toolkits/VectorStoreToolkit.py

@@ -3,7 +3,7 @@ from typing import Union
 from langchain.agents.agent_toolkits.vectorstore.toolkit import VectorStoreInfo, VectorStoreToolkit
 
 from langflow.custom import CustomComponent
-from langflow.field_typing import BaseLanguageModel, Tool
+from langflow.field_typing import LanguageModel, Tool
 
 
 class VectorStoreToolkitComponent(CustomComponent):
@@ -19,6 +19,6 @@ class VectorStoreToolkitComponent(CustomComponent):
     def build(
         self,
         vectorstore_info: VectorStoreInfo,
-        llm: BaseLanguageModel,
+        llm: LanguageModel,
     ) -> Union[Tool, VectorStoreToolkit]:
         return VectorStoreToolkit(vectorstore_info=vectorstore_info, llm=llm)

src/backend/base/langflow/field_typing/constants.py

@@ -15,7 +15,9 @@ from langchain_core.tools import Tool
 from langchain_core.vectorstores import VectorStore
 from langchain_text_splitters import TextSplitter
 
+
 NestedDict = Dict[str, Union[str, Dict]]
+type LanguageModel = Union[BaseLanguageModel, BaseLLM, BaseChatModel]
 
 
 class Object:
@@ -58,4 +60,5 @@ CUSTOM_COMPONENT_SUPPORTED_TYPES = {
     "Text": Text,
     "Object": Object,
     "Callable": Callable,
+    "LanguageModel": LanguageModel,
 }

src/backend/base/langflow/initial_setup/starter_projects/Basic Prompting (Hello, world!).json

@@ -611,9 +611,9 @@
                 "display_name": "Language Model",
                 "method": "build_model",
                 "name": "model_output",
-                "selected": "BaseLanguageModel",
+                "selected": "LanguageModel",
                 "types": [
-                  "BaseLanguageModel"
+                  "LanguageModel"
                 ],
                 "value": "__UNDEFINED__"
               }
@@ -637,7 +637,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import BaseLanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> BaseLanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
+                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> LanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
               },
               "input_value": {
                 "advanced": false,

src/backend/base/langflow/initial_setup/starter_projects/Langflow Document QA.json

@@ -630,7 +630,7 @@
             "description": "A generic file loader.",
             "display_name": "File",
             "documentation": "",
-            "edited": true,
+            "edited": false,
             "field_order": [
               "path",
               "silent_errors"
@@ -785,9 +785,9 @@
                 "display_name": "Language Model",
                 "method": "build_model",
                 "name": "model_output",
-                "selected": "BaseLanguageModel",
+                "selected": "LanguageModel",
                 "types": [
-                  "BaseLanguageModel"
+                  "LanguageModel"
                 ],
                 "value": "__UNDEFINED__"
               }
@@ -811,7 +811,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import BaseLanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> BaseLanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
+                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> LanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
               },
               "input_value": {
                 "advanced": false,

src/backend/base/langflow/initial_setup/starter_projects/Langflow Memory Conversation.json

@@ -687,9 +687,9 @@
                 "display_name": "Language Model",
                 "method": "build_model",
                 "name": "model_output",
-                "selected": "BaseLanguageModel",
+                "selected": "LanguageModel",
                 "types": [
-                  "BaseLanguageModel"
+                  "LanguageModel"
                 ],
                 "value": "__UNDEFINED__"
               }
@@ -713,7 +713,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import BaseLanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> BaseLanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
+                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> LanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
               },
               "input_value": {
                 "advanced": false,

src/backend/base/langflow/initial_setup/starter_projects/Langflow Prompt Chaining.json

@@ -1099,9 +1099,9 @@
                 "display_name": "Language Model",
                 "method": "build_model",
                 "name": "model_output",
-                "selected": "BaseLanguageModel",
+                "selected": "LanguageModel",
                 "types": [
-                  "BaseLanguageModel"
+                  "LanguageModel"
                 ],
                 "value": "__UNDEFINED__"
               }
@@ -1124,7 +1124,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import BaseLanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> BaseLanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
+                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> LanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
               },
               "input_value": {
                 "advanced": false,
@@ -1512,9 +1512,9 @@
                 "display_name": "Language Model",
                 "method": "build_model",
                 "name": "model_output",
-                "selected": "BaseLanguageModel",
+                "selected": "LanguageModel",
                 "types": [
-                  "BaseLanguageModel"
+                  "LanguageModel"
                 ],
                 "value": "__UNDEFINED__"
               }
@@ -1537,7 +1537,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import BaseLanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> BaseLanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
+                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> LanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
               },
               "input_value": {
                 "advanced": false,

src/backend/base/langflow/initial_setup/starter_projects/VectorStore-RAG-Flows.json

@@ -495,7 +495,7 @@
             "description": "Display a text output in the Playground.",
             "display_name": "Extracted Chunks",
             "documentation": "",
-            "edited": true,
+            "edited": false,
             "field_order": [
               "input_value"
             ],
@@ -1042,9 +1042,9 @@
                 "display_name": "Language Model",
                 "method": "build_model",
                 "name": "model_output",
-                "selected": "BaseLanguageModel",
+                "selected": "LanguageModel",
                 "types": [
-                  "BaseLanguageModel"
+                  "LanguageModel"
                 ],
                 "value": "__UNDEFINED__"
               }
@@ -1067,7 +1067,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import BaseLanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> BaseLanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
+                "value": "import operator\nfrom functools import reduce\n\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom langflow.base.constants import STREAM_INFO_TEXT\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.base.models.openai_constants import MODEL_NAMES\nfrom langflow.field_typing import LanguageModel\nfrom langflow.inputs import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.message import Message\nfrom langflow.template import Output\n\n\nclass OpenAIModelComponent(LCModelComponent):\n    display_name = \"OpenAI\"\n    description = \"Generates text using OpenAI LLMs.\"\n    icon = \"OpenAI\"\n\n    inputs = [\n        MessageInput(name=\"input_value\", display_name=\"Input\"),\n        IntInput(\n            name=\"max_tokens\",\n            display_name=\"Max Tokens\",\n            advanced=True,\n            info=\"The maximum number of tokens to generate. Set to 0 for unlimited tokens.\",\n        ),\n        DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n        DictInput(\n            name=\"output_schema\",\n            is_list=True,\n            display_name=\"Schema\",\n            advanced=True,\n            info=\"The schema for the Output of the model. You must pass the word JSON in the prompt. If left blank, JSON mode will be disabled.\",\n        ),\n        DropdownInput(\n            name=\"model_name\", display_name=\"Model Name\", advanced=False, options=MODEL_NAMES, value=MODEL_NAMES[0]\n        ),\n        StrInput(\n            name=\"openai_api_base\",\n            display_name=\"OpenAI API Base\",\n            advanced=True,\n            info=\"The base URL of the OpenAI API. Defaults to https://api.openai.com/v1. You can change this to use other APIs like JinaChat, LocalAI and Prem.\",\n        ),\n        SecretStrInput(\n            name=\"openai_api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"The OpenAI API Key to use for the OpenAI model.\",\n            advanced=False,\n            value=\"OPENAI_API_KEY\",\n        ),\n        FloatInput(name=\"temperature\", display_name=\"Temperature\", value=0.1),\n        BoolInput(name=\"stream\", display_name=\"Stream\", info=STREAM_INFO_TEXT, advanced=True),\n        StrInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"System message to pass to the model.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"seed\",\n            display_name=\"Seed\",\n            info=\"The seed controls the reproducibility of the job.\",\n            advanced=True,\n            value=1,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Text\", name=\"text_output\", method=\"text_response\"),\n        Output(display_name=\"Language Model\", name=\"model_output\", method=\"build_model\"),\n    ]\n\n    def text_response(self) -> Message:\n        input_value = self.input_value\n        stream = self.stream\n        system_message = self.system_message\n        output = self.build_model()\n        result = self.get_chat_result(output, stream, input_value, system_message)\n        self.status = result\n        return result\n\n    def build_model(self) -> LanguageModel:\n        # self.output_schea is a list of dictionaries\n        # let's convert it to a dictionary\n        output_schema_dict: dict[str, str] = reduce(operator.ior, self.output_schema or {}, {})\n        openai_api_key = self.openai_api_key\n        temperature = self.temperature\n        model_name: str = self.model_name\n        max_tokens = self.max_tokens\n        model_kwargs = self.model_kwargs\n        openai_api_base = self.openai_api_base or \"https://api.openai.com/v1\"\n        json_mode = bool(output_schema_dict)\n        seed = self.seed\n        if openai_api_key:\n            api_key = SecretStr(openai_api_key)\n        else:\n            api_key = None\n        output = ChatOpenAI(\n            max_tokens=max_tokens or None,\n            model_kwargs=model_kwargs or {},\n            model=model_name,\n            base_url=openai_api_base,\n            api_key=api_key,\n            temperature=temperature or 0.1,\n            seed=seed,\n        )\n        if json_mode:\n            output = output.with_structured_output(schema=output_schema_dict, method=\"json_mode\")\n\n        return output\n"
               },
               "input_value": {
                 "advanced": false,
@@ -2168,7 +2168,7 @@
             "description": "Split text into chunks of a specified length.",
             "display_name": "Recursive Character Text Splitter",
             "documentation": "https://docs.langflow.org/components/text-splitters#recursivecharactertextsplitter",
-            "edited": true,
+            "edited": false,
             "field_order": [
               "chunk_size",
               "chunk_overlap",

src/frontend/src/utils/styleUtils.ts

@@ -284,6 +284,7 @@ export const nodeColors: { [char: string]: string } = {
   Prompt: "#7c3aed",
   Embeddings: "#10b981",
   BaseLanguageModel: "#c026d3",
+  LanguageModel: "#c026d3",
 };
 
 export const nodeNames: { [char: string]: string } = {