from_llm() — langchain Function Reference
Architecture documentation for the from_llm() function in base.py from the langchain codebase.
Entity Profile
Dependency Diagram
graph TD 2a359647_ad3b_4021_eb9b_23a432e1e2eb["from_llm()"] 5aa1201d_23fd_f122_acb5_563cb1cc3cb3["BaseQAWithSourcesChain"] 2a359647_ad3b_4021_eb9b_23a432e1e2eb -->|defined in| 5aa1201d_23fd_f122_acb5_563cb1cc3cb3 style 2a359647_ad3b_4021_eb9b_23a432e1e2eb fill:#6366f1,stroke:#818cf8,color:#fff
Relationship Graph
Source Code
libs/langchain/langchain_classic/chains/qa_with_sources/base.py lines 59–86
def from_llm(
cls,
llm: BaseLanguageModel,
document_prompt: BasePromptTemplate = EXAMPLE_PROMPT,
question_prompt: BasePromptTemplate = QUESTION_PROMPT,
combine_prompt: BasePromptTemplate = COMBINE_PROMPT,
**kwargs: Any,
) -> BaseQAWithSourcesChain:
"""Construct the chain from an LLM."""
llm_question_chain = LLMChain(llm=llm, prompt=question_prompt)
llm_combine_chain = LLMChain(llm=llm, prompt=combine_prompt)
combine_results_chain = StuffDocumentsChain(
llm_chain=llm_combine_chain,
document_prompt=document_prompt,
document_variable_name="summaries",
)
reduce_documents_chain = ReduceDocumentsChain(
combine_documents_chain=combine_results_chain,
)
combine_documents_chain = MapReduceDocumentsChain(
llm_chain=llm_question_chain,
reduce_documents_chain=reduce_documents_chain,
document_variable_name="context",
)
return cls(
combine_documents_chain=combine_documents_chain,
**kwargs,
)
Domain
Subdomains
Source
Frequently Asked Questions
What does from_llm() do?
from_llm() is a function in the langchain codebase, defined in libs/langchain/langchain_classic/chains/qa_with_sources/base.py.
Where is from_llm() defined?
from_llm() is defined in libs/langchain/langchain_classic/chains/qa_with_sources/base.py at line 59.
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free