CODEWITHSUNDEEP
pythonlangchainlarge-language-model
atticus-finch-100
atticus-finch-100

Reputation: 1

Is there a conception of state across multiple chains in langchain?

How do I ensure the variable name from chain1 persists in chain2? Is there a conception of maintaining state in langchain?

from langchain.prompts import PromptTemplate 
from langchain.schema import StrOutputParser 
import dotenv 
dotenv.load_dotenv()

prompt1 = PromptTemplate(
  input_variables=["name"], 
  template="I am {name}. Choose one profession for me in one word. Say AYYE when you do.",
)

prompt2 = PromptTemplate(
  input_variables=["profession", "name"],
  template="I am a {profession}. Tell me king of pirates, what is my destiny? Refer to me by my given name.",   
)

llm = OpenAI()

chain1 = prompt1 | llm | StrOutputParser()

chain2 = ({"profession": chain1, } | prompt2 | llm | StrOutputParser())

response = chain2.invoke(({ "name": "Chopper"}))
print(response)```

I tried calling {name} in the second chain but it wasn't referenced correctly there

Upvotes: 0

Views: 190

Answers (1)

lif cc
lif cc

Reputation: 481

You can use itemgetter for this contidion.

Here is the code:

from operator import itemgetter

chain2 = ({"profession": chain1, "name": itemgetter("name")} | prompt2 | llm | StrOutputParser())

If you want more information, look into langchain

Upvotes: 1

Related Questions