You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I added a very descriptive title to this question.
I searched the LangChain documentation with the integrated search.
I used the GitHub search to find a similar question and didn't find it.
Commit to Help
I commit to help with one of those options 👆
Example Code
tools= [{
"type": "function",
"function": {
"name": "write_paragraph",
"description": "Write a paragraph about a given topic.",
"parameters": {
"type": "object",
"properties": {
"paragraph": {
"type": "string",
"description": "The paragraph to write."
}
},
"required": [
"paragraph"
],
},
}
}]
Description
We having being self maintaining llm calls from multiple provider and now would like to use langchain to solve this issue. However, I found that langchain forced us to provide a callable func to create tools:langchain_core.tools.Tool, which is not required by any of the foundation model providers. Assuming that we want to replicate the exact behavior of a llm call with the same system prompt, messages and tools
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Checked other resources
Commit to Help
Example Code
Description
We having being self maintaining llm calls from multiple provider and now would like to use langchain to solve this issue. However, I found that langchain forced us to provide a callable
func
to create tools:langchain_core.tools.Tool
, which is not required by any of the foundation model providers. Assuming that we want to replicate the exact behavior of a llm call with the samesystem prompt
,messages
andtools
System Info
irrelevant
Beta Was this translation helpful? Give feedback.
All reactions