Doesn't langchain support other LLM agents? For example, a custom LLM proxy address #8847
Replies: 1 comment
-
Answer generated by a 🤖 AnswerHello, Yes, LangChain does support other language model agents. The Python framework provides a variety of toolkits for different services, including Amadeus, Azure Cognitive Services, Gmail, Jira, Office365, OpenAPI, PowerBI, SQLDatabase, SparkSQL, VectorStore, and more. Here is an example of how you can use these toolkits: from langchain.agents.agent_toolkits.amadeus.toolkit import AmadeusToolkit
from langchain.agents.agent_toolkits.azure_cognitive_services import (
AzureCognitiveServicesToolkit,
)
...
from langchain.agents.agent_toolkits.office365.toolkit import O365Toolkit
from langchain.agents.agent_toolkits.openapi.base import create_openapi_agent
...
from langchain.agents.agent_toolkits.powerbi.base import create_pbi_agent
...
from langchain.agents.agent_toolkits.sql.base import create_sql_agent
from langchain.agents.agent_toolkits.sql.toolkit import SQLDatabaseToolkit
...
from langchain.agents.agent_toolkits.vectorstore.base import (
create_vectorstore_agent,
create_vectorstore_router_agent,
)
... You can find more details in the LangChain repository. As for your question about a custom LLM proxy address, there is no direct evidence in the provided context. However, considering the variety of toolkits and agents available, it is likely that LangChain could be extended to support a custom LLM proxy address. Regarding a user-friendly interface, the toolkits and agents are designed to be used programmatically, which suggests that they are intended to be user-friendly for developers. There was a similar issue about incorporating MLC with LangChain, which might be of interest to you. You can find it here. If you need more specific information or if there's something else you'd like to know, please provide more details. Best regards, SourcesThis response is meant to be useful, save you time, and share context. It is not meant to be a precise solution, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Or is there an interface that is easy for us to use?
Beta Was this translation helpful? Give feedback.
All reactions