Skip to content

armgit / storm

Public Imported from GitHub
0

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Updated duckduckgo retrievers to be parsed

zenith110932adfc4e29b
diff --git a/.gitignore b/.gitignore
index 25d79a5..46767c6 100644
--- a/.gitignore
+++ b/.gitignore
@@ -23,4 +23,5 @@ build/
secrets.toml
*.log
*/assertion.log
-*results/
\ No newline at end of file
+*results/
+.venv/
\ No newline at end of file
diff --git a/examples/run_storm_wiki_claude.py b/examples/run_storm_wiki_claude.py
index ccefc37..d15595a 100644
--- a/examples/run_storm_wiki_claude.py
+++ b/examples/run_storm_wiki_claude.py
@@ -61,7 +61,7 @@ def main(args):
# STORM is a knowledge curation system which consumes information from the retrieval module.
# Currently, the information source is the Internet and we use search engine API as the retrieval module.
- match args.retriver:
+ match args.retriever:
case 'bing':
rm = BingSearch(bing_search_api=os.getenv('BING_SEARCH_API_KEY'), k=engine_args.search_top_k)
case 'you':
diff --git a/examples/run_storm_wiki_deepseek.py b/examples/run_storm_wiki_deepseek.py
index 8ac5e99..deab4dc 100644
--- a/examples/run_storm_wiki_deepseek.py
+++ b/examples/run_storm_wiki_deepseek.py
@@ -88,7 +88,7 @@ def main(args):
# STORM is a knowledge curation system which consumes information from the retrieval module.
# Currently, the information source is the Internet and we use search engine API as the retrieval module.
- match args.retriver:
+ match args.retriever:
case 'bing':
rm = BingSearch(bing_search_api=os.getenv('BING_SEARCH_API_KEY'), k=engine_args.search_top_k)
case 'you':
diff --git a/examples/run_storm_wiki_gemini.py b/examples/run_storm_wiki_gemini.py
index 81d430f..501aae9 100644
--- a/examples/run_storm_wiki_gemini.py
+++ b/examples/run_storm_wiki_gemini.py
@@ -63,7 +63,7 @@ def main(args):
# STORM is a knowledge curation system which consumes information from the retrieval module.
# Currently, the information source is the Internet and we use search engine API as the retrieval module.
- match args.retriver:
+ match args.retriever:
case 'bing':
rm = BingSearch(bing_search_api=os.getenv('BING_SEARCH_API_KEY'), k=engine_args.search_top_k)
case 'you':
diff --git a/examples/run_storm_wiki_gpt.py b/examples/run_storm_wiki_gpt.py
index 530b8a1..a665ed8 100644
--- a/examples/run_storm_wiki_gpt.py
+++ b/examples/run_storm_wiki_gpt.py
@@ -73,7 +73,7 @@ def main(args):
# STORM is a knowledge curation system which consumes information from the retrieval module.
# Currently, the information source is the Internet and we use search engine API as the retrieval module.
- match args.retriver:
+ match args.retriever:
case 'bing':
rm = BingSearch(bing_search_api=os.getenv('BING_SEARCH_API_KEY'), k=engine_args.search_top_k)
case 'you':
diff --git a/examples/run_storm_wiki_mistral.py b/examples/run_storm_wiki_mistral.py
index b4ecc60..eb9594d 100644
--- a/examples/run_storm_wiki_mistral.py
+++ b/examples/run_storm_wiki_mistral.py
@@ -59,7 +59,7 @@ def main(args):
# STORM is a knowledge curation system which consumes information from the retrieval module.
# Currently, the information source is the Internet and we use search engine API as the retrieval module.
- match args.retriver:
+ match args.retriever:
case 'bing':
rm = BingSearch(bing_search_api=os.getenv('BING_SEARCH_API_KEY'), k=engine_args.search_top_k)
case 'you':
diff --git a/examples/run_storm_wiki_ollama.py b/examples/run_storm_wiki_ollama.py
index af35572..78e0fcf 100644
--- a/examples/run_storm_wiki_ollama.py
+++ b/examples/run_storm_wiki_ollama.py
@@ -61,7 +61,7 @@ def main(args):
# STORM is a knowledge curation system which consumes information from the retrieval module.
# Currently, the information source is the Internet and we use search engine API as the retrieval module.
- match args.retriver:
+ match args.retriever:
case 'bing':
rm = BingSearch(bing_search_api=os.getenv('BING_SEARCH_API_KEY'), k=engine_args.search_top_k)
case 'you':
diff --git a/knowledge_storm/rm.py b/knowledge_storm/rm.py
index afb7942..3d0a5fb 100644
--- a/knowledge_storm/rm.py
+++ b/knowledge_storm/rm.py
@@ -511,6 +511,7 @@ class BraveRM(dspy.Retrieve):
return collected_results
class DuckDuckGoSearchRM(dspy.Retrieve):
+ """Retrieve information from custom queries using DuckDuckGo."""
def __init__(
self,
k: int =3,
@@ -520,7 +521,6 @@ class DuckDuckGoSearchRM(dspy.Retrieve):
webpage_helper_max_threads=10,
safe_search: str = 'On',
region: str = 'us-en'
- **kwargs,
):
"""
Params:
@@ -538,7 +538,6 @@ class DuckDuckGoSearchRM(dspy.Retrieve):
max_thread_num=webpage_helper_max_threads,
)
self.usage = 0
-
# All params for search can be found here:
# https://duckduckgo.com/duckduckgo-help-pages/settings/params/