Kevin Hu
commited on
Commit
·
aa09acb
1
Parent(s):
210b45f
refactor name of duckduckgo (#1496)
Browse files### What problem does this PR solve?
### Type of change
- [x] Refactoring
graph/component/__init__.py
CHANGED
@@ -10,7 +10,7 @@ from .message import Message, MessageParam
|
|
10 |
from .rewrite import RewriteQuestion, RewriteQuestionParam
|
11 |
from .keyword import KeywordExtract, KeywordExtractParam
|
12 |
from .baidu import Baidu, BaiduParam
|
13 |
-
from .
|
14 |
|
15 |
|
16 |
def component_class(class_name):
|
|
|
10 |
from .rewrite import RewriteQuestion, RewriteQuestionParam
|
11 |
from .keyword import KeywordExtract, KeywordExtractParam
|
12 |
from .baidu import Baidu, BaiduParam
|
13 |
+
from .duckduckgo import DuckDuckGo, DuckDuckGoParam
|
14 |
|
15 |
|
16 |
def component_class(class_name):
|
graph/component/{duckduckgosearch.py → duckduckgo.py}
RENAMED
@@ -1,62 +1,62 @@
|
|
1 |
-
#
|
2 |
-
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
|
3 |
-
#
|
4 |
-
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
-
# you may not use this file except in compliance with the License.
|
6 |
-
# You may obtain a copy of the License at
|
7 |
-
#
|
8 |
-
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
-
#
|
10 |
-
# Unless required by applicable law or agreed to in writing, software
|
11 |
-
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
-
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
-
# See the License for the specific language governing permissions and
|
14 |
-
# limitations under the License.
|
15 |
-
#
|
16 |
-
import random
|
17 |
-
from abc import ABC
|
18 |
-
from functools import partial
|
19 |
-
from duckduckgo_search import DDGS
|
20 |
-
import pandas as pd
|
21 |
-
|
22 |
-
from graph.component.base import ComponentBase, ComponentParamBase
|
23 |
-
|
24 |
-
|
25 |
-
class
|
26 |
-
"""
|
27 |
-
Define the
|
28 |
-
"""
|
29 |
-
|
30 |
-
def __init__(self):
|
31 |
-
super().__init__()
|
32 |
-
self.top_n = 10
|
33 |
-
self.channel = "text"
|
34 |
-
|
35 |
-
def check(self):
|
36 |
-
self.check_positive_integer(self.top_n, "Top N")
|
37 |
-
self.check_valid_value(self.channel, "Web Search or News", ["text", "news"])
|
38 |
-
|
39 |
-
|
40 |
-
class
|
41 |
-
component_name = "
|
42 |
-
|
43 |
-
def _run(self, history, **kwargs):
|
44 |
-
ans = self.get_input()
|
45 |
-
ans = " - ".join(ans["content"]) if "content" in ans else ""
|
46 |
-
if not ans:
|
47 |
-
return
|
48 |
-
|
49 |
-
if self.channel == "text":
|
50 |
-
with DDGS() as ddgs:
|
51 |
-
# {'title': '', 'href': '', 'body': ''}
|
52 |
-
duck_res = [{"content": '<a href="' + i["href"] + '">' + i["title"] + '</a> ' + i["body"]} for i in
|
53 |
-
ddgs.text(ans, max_results=self._param.top_n)]
|
54 |
-
elif self.channel == "news":
|
55 |
-
with DDGS() as ddgs:
|
56 |
-
# {'date': '', 'title': '', 'body': '', 'url': '', 'image': '', 'source': ''}
|
57 |
-
duck_res = [{"content": '<a href="' + i["url"] + '">' + i["title"] + '</a> ' + i["body"]} for i in
|
58 |
-
ddgs.news(ans, max_results=self._param.top_n)]
|
59 |
-
|
60 |
-
df = pd.DataFrame(duck_res)
|
61 |
-
print(df, ":::::::::::::::::::::::::::::::::")
|
62 |
-
return df
|
|
|
1 |
+
#
|
2 |
+
# Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
|
3 |
+
#
|
4 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
5 |
+
# you may not use this file except in compliance with the License.
|
6 |
+
# You may obtain a copy of the License at
|
7 |
+
#
|
8 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
9 |
+
#
|
10 |
+
# Unless required by applicable law or agreed to in writing, software
|
11 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
12 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13 |
+
# See the License for the specific language governing permissions and
|
14 |
+
# limitations under the License.
|
15 |
+
#
|
16 |
+
import random
|
17 |
+
from abc import ABC
|
18 |
+
from functools import partial
|
19 |
+
from duckduckgo_search import DDGS
|
20 |
+
import pandas as pd
|
21 |
+
|
22 |
+
from graph.component.base import ComponentBase, ComponentParamBase
|
23 |
+
|
24 |
+
|
25 |
+
class DuckDuckGoParam(ComponentParamBase):
|
26 |
+
"""
|
27 |
+
Define the DuckDuckGo component parameters.
|
28 |
+
"""
|
29 |
+
|
30 |
+
def __init__(self):
|
31 |
+
super().__init__()
|
32 |
+
self.top_n = 10
|
33 |
+
self.channel = "text"
|
34 |
+
|
35 |
+
def check(self):
|
36 |
+
self.check_positive_integer(self.top_n, "Top N")
|
37 |
+
self.check_valid_value(self.channel, "Web Search or News", ["text", "news"])
|
38 |
+
|
39 |
+
|
40 |
+
class DuckDuckGo(ComponentBase, ABC):
|
41 |
+
component_name = "DuckDuckGo"
|
42 |
+
|
43 |
+
def _run(self, history, **kwargs):
|
44 |
+
ans = self.get_input()
|
45 |
+
ans = " - ".join(ans["content"]) if "content" in ans else ""
|
46 |
+
if not ans:
|
47 |
+
return DuckDuckGo.be_output(self._param.no)
|
48 |
+
|
49 |
+
if self.channel == "text":
|
50 |
+
with DDGS() as ddgs:
|
51 |
+
# {'title': '', 'href': '', 'body': ''}
|
52 |
+
duck_res = [{"content": '<a href="' + i["href"] + '">' + i["title"] + '</a> ' + i["body"]} for i in
|
53 |
+
ddgs.text(ans, max_results=self._param.top_n)]
|
54 |
+
elif self.channel == "news":
|
55 |
+
with DDGS() as ddgs:
|
56 |
+
# {'date': '', 'title': '', 'body': '', 'url': '', 'image': '', 'source': ''}
|
57 |
+
duck_res = [{"content": '<a href="' + i["url"] + '">' + i["title"] + '</a> ' + i["body"]} for i in
|
58 |
+
ddgs.news(ans, max_results=self._param.top_n)]
|
59 |
+
|
60 |
+
df = pd.DataFrame(duck_res)
|
61 |
+
print(df, ":::::::::::::::::::::::::::::::::")
|
62 |
+
return df
|