langchain/docs/modules/chains/generic/from_hub.ipynb

Loading from LangChainHub

This notebook covers how to load chains from LangChainHub.

In [5]:

from langchain.chains import load_chain

chain = load_chain("lc://chains/llm-math/chain.json")

In [3]:

chain.run("whats 2 raised to .12")

Out [3]:

> Entering new LLMMathChain chain...
whats 2 raised to .12
Answer: 1.0791812460476249
> Finished chain.

'Answer: 1.0791812460476249'

Sometimes chains will require extra arguments that were not serialized with the chain. For example, a chain that does question answering over a vector database will require a vector database.

In [1]:

from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from langchain import OpenAI, VectorDBQA

In [3]:

from langchain.document_loaders import TextLoader
loader = TextLoader('../../state_of_the_union.txt')
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(texts, embeddings)

Running Chroma using direct local API.
Using DuckDB in-memory for database. Data will be transient.

In [6]:

chain = load_chain("lc://chains/vector-db-qa/stuff/chain.json", vectorstore=vectorstore)

In [7]:

query = "What did the president say about Ketanji Brown Jackson"
chain.run(query)

Out [7]:

" The president said that Ketanji Brown Jackson is a Circuit Court of Appeals Judge, one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans, and will continue Justice Breyer's legacy of excellence."

In [ ]: