from_llm(
cls,
vectorstore: VectorStore,
llm: BaseLLM,
search: GoogleSearchAPIWrapper,
| Name | Type | Description |
|---|---|---|
vectorstore* | VectorStore | Vector store for storing web pages |
llm* | BaseLLM | llm for search question generation |
search* | GoogleSearchAPIWrapper | GoogleSearchAPIWrapper |
prompt | Optional[BasePromptTemplate] | Default: None |
num_search_results | int | Default: 1 |
text_splitter | RecursiveCharacterTextSplitter | Default: RecursiveCharacterTextSplitter(chunk_size=1500, chunk_overlap=150) |
trust_env | bool | Default: False |
allow_dangerous_requests | bool | Default: False |
Initialize from llm using default template.
prompt to generating search questions
Number of pages per Google search
Text splitter for splitting web pages into chunks
Whether to use the http_proxy/https_proxy env variables or check .netrc for proxy configuration
A flag to force users to acknowledge the risks of SSRF attacks when using this retriever