mirror of
				https://github.com/deepset-ai/haystack.git
				synced 2025-10-31 01:39:45 +00:00 
			
		
		
		
	 be25655663
			
		
	
	
		be25655663
		
			
		
	
	
	
	
		
			
			* Initial commit, add search_engine * Add TopPSampler * Add more TopPSampler unit tests * Remove SearchEngineSampler (converted to TopPSampler) * Add some basic WebSearch unit tests * Rename unit tests * Add WebRetriever into agent_tools * Adjust to WebRetriever * Add WebRetriever mode [snippet|document] * Minor changes * SerperDev: add peopleAlsoAsk search results * First agent for hotpotqa * Making WebRetriever work on hotpotqa * refactor: minor WebRetriever improvements (#4377) * refactor: remove doc ids rebuild + antecipate cache * refactor: improve caching, fix Document ids * Minor WebRetriever improvements * Overlooked minor fixes * feat: add Bing API as search engine * refactor: let kwargs pass-through * feat: increase search context * check sampler result, improve batch typing * refactor: increase mypy compliance * Initial commit, add search_engine * Add TopPSampler * Add more TopPSampler unit tests * Remove SearchEngineSampler (converted to TopPSampler) * Add some basic WebSearch unit tests * Rename unit tests * Add WebRetriever into agent_tools * Adjust to WebRetriever * Add WebRetriever mode [snippet|document] * Minor changes * SerperDev: add peopleAlsoAsk search results * First agent for hotpotqa * Making WebRetriever work on hotpotqa * refactor: minor WebRetriever improvements (#4377) * refactor: remove doc ids rebuild + antecipate cache * refactor: improve caching, fix Document ids * Minor WebRetriever improvements * Overlooked minor fixes * feat: add Bing API as search engine * refactor: let kwargs pass-through * feat: increase search context * check sampler result, improve batch typing * refactor: increase mypy compliance * Fix mypy * Minor example fixes * Fix the descriptions * PR feedback updates * More fixes * TopPSampler: handle top p None value, add unit test * Add top_k to WebSearch * Use boilerpy3 instead trafilatura * Remove date finding * Add more WebRetriever docs * Refactor long methods * making the preprocessor optional * hide WebSearch and make NeuralWebSearch a pipeline * remove unused imports * add WebQAPipeline and split example into two * change example search engine to SerperDev * Turn off progress bars in WebRetriever's PreProcesssor * Agent tool examples - final updates * Add webqa test, search results ranking scores * Better answer box handling for SerperDev and SerpAPI * Minor fixes * pylint * pylint fixes * extract TopPSampler from WebRetriever * use sampler only for WebRetriever modes other than snippet * add web retriever tests * add web retriever tests * exclude rdflib@6.3.2 due to license issues * add test for preprocessed docs and kwargs examples in docstrings * Move test_webqa_pipeline to test/pipelines * change docstring for join_documents_and_scores * Use WebQAPipeline in examples/web_lfqa.py * Use WebQAPipeline in examples/web_lfqa.py * Move test_webqa_pipeline to e2e * Updated lg * Sampler added automatically in WebQAPipeline, no need to add it * Updated lg * Updated lg * :ignore Update agent tools examples to new templates (#4503) * Update examples to new templates * Add print back * fix linting and black format issues --------- Co-authored-by: Daniel Bichuetti <daniel.bichuetti@gmail.com> Co-authored-by: agnieszka-m <amarzec13@gmail.com> Co-authored-by: Julian Risch <julian.risch@deepset.ai>
		
			
				
	
	
		
			36 lines
		
	
	
		
			1.1 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			36 lines
		
	
	
		
			1.1 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
| import os
 | |
| from haystack.nodes import PromptNode
 | |
| from haystack.nodes.retriever.web import WebRetriever
 | |
| from haystack.pipelines import WebQAPipeline
 | |
| 
 | |
| search_key = os.environ.get("SERPERDEV_API_KEY")
 | |
| if not search_key:
 | |
|     raise ValueError("Please set the SERPERDEV_API_KEY environment variable")
 | |
| 
 | |
| openai_key = os.environ.get("OPENAI_API_KEY")
 | |
| if not search_key:
 | |
|     raise ValueError("Please set the OPENAI_API_KEY environment variable")
 | |
| 
 | |
| prompt_node = PromptNode(
 | |
|     "text-davinci-003",
 | |
|     api_key=openai_key,
 | |
|     max_length=256,
 | |
|     default_prompt_template="question-answering-with-document-scores",
 | |
| )
 | |
| web_retriever = WebRetriever(api_key=search_key)
 | |
| pipeline = WebQAPipeline(retriever=web_retriever, prompt_node=prompt_node)
 | |
| 
 | |
| questions = [
 | |
|     "Who won the 1971 San Francisco mayoral election?",
 | |
|     "Where was Jeremy McKinnon born?",
 | |
|     "What river is near Dundalk, Ireland?",
 | |
|     "Who is Kyle Moran?",
 | |
|     "What party does Joseph Alioto belong to?",
 | |
|     "When was the Democratic Party founded?",
 | |
|     "Who is Olivia Wilde's boyfriend?",
 | |
| ]
 | |
| 
 | |
| for question in questions:
 | |
|     response = pipeline.run(question)
 | |
|     print(f"{question} - {response['answers'][0].answer}")
 |