Skip to content

Commit 3b90ebd

Browse files
VinciGit00VinciGit00
committed
add new examples
1 parent 9f73d7a commit 3b90ebd

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

41 files changed

+2516
-54
lines changed

‎examples/anthropic/.env.example

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
ANTHROPIC_API_KEY="YOUR ANTHROPIC API KEY"

‎examples/anthropic/csv_scraper_haiku.py

Lines changed: 62 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,62 @@
1+
"""
2+
Basic example of scraping pipeline using CSVScraperGraph from CSV documents
3+
"""
4+
5+
import os
6+
from dotenv import load_dotenv
7+
import pandas as pd
8+
from scrapegraphai.graphs import CSVScraperGraph
9+
from scrapegraphai.utils import convert_to_csv, convert_to_json, prettify_exec_info
10+
11+
load_dotenv()
12+
13+
# ************************************************
14+
# Read the CSV file
15+
# ************************************************
16+
17+
FILE_NAME = "inputs/username.csv"
18+
curr_dir = os.path.dirname(os.path.realpath(__file__))
19+
file_path = os.path.join(curr_dir, FILE_NAME)
20+
21+
text = pd.read_csv(file_path)
22+
23+
# ************************************************
24+
# Define the configuration for the graph
25+
# ************************************************
26+
27+
# required environment variables in .env
28+
# HUGGINGFACEHUB_API_TOKEN
29+
# ANTHROPIC_API_KEY
30+
load_dotenv()
31+
32+
graph_config = {
33+
"llm": {
34+
"api_key": os.getenv("ANTHROPIC_API_KEY"),
35+
"model": "claude-3-haiku-20240307",
36+
"max_tokens": 4000
37+
},
38+
}
39+
40+
# ************************************************
41+
# Create the CSVScraperGraph instance and run it
42+
# ************************************************
43+
44+
csv_scraper_graph = CSVScraperGraph(
45+
prompt="List me all the last names",
46+
source=str(text), # Pass the content of the file, not the file object
47+
config=graph_config
48+
)
49+
50+
result = csv_scraper_graph.run()
51+
print(result)
52+
53+
# ************************************************
54+
# Get graph execution info
55+
# ************************************************
56+
57+
graph_exec_info = csv_scraper_graph.get_execution_info()
58+
print(prettify_exec_info(graph_exec_info))
59+
60+
# Save to json or csv
61+
convert_to_csv(result, "result")
62+
convert_to_json(result, "result")

‎examples/anthropic/custom_graph_haiku.py

Lines changed: 110 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,110 @@
1+
"""
2+
Example of custom graph using existing nodes
3+
"""
4+
5+
import os
6+
from dotenv import load_dotenv
7+
8+
from langchain_openai import OpenAIEmbeddings
9+
from scrapegraphai.models import OpenAI
10+
from scrapegraphai.graphs import BaseGraph
11+
from scrapegraphai.nodes import FetchNode, ParseNode, RAGNode, GenerateAnswerNode, RobotsNode
12+
load_dotenv()
13+
14+
# ************************************************
15+
# Define the configuration for the graph
16+
# ************************************************
17+
18+
graph_config = {
19+
"llm": {
20+
"api_key": os.getenv("ANTHROPIC_API_KEY"),
21+
"model": "claude-3-haiku-20240307",
22+
"max_tokens": 4000
23+
},
24+
}
25+
26+
# ************************************************
27+
# Define the graph nodes
28+
# ************************************************
29+
30+
llm_model = OpenAI(graph_config["llm"])
31+
embedder = OpenAIEmbeddings(api_key=llm_model.openai_api_key)
32+
33+
# define the nodes for the graph
34+
robot_node = RobotsNode(
35+
input="url",
36+
output=["is_scrapable"],
37+
node_config={
38+
"llm_model": llm_model,
39+
"force_scraping": True,
40+
"verbose": True,
41+
}
42+
)
43+
44+
fetch_node = FetchNode(
45+
input="url | local_dir",
46+
output=["doc", "link_urls", "img_urls"],
47+
node_config={
48+
"verbose": True,
49+
"headless": True,
50+
}
51+
)
52+
parse_node = ParseNode(
53+
input="doc",
54+
output=["parsed_doc"],
55+
node_config={
56+
"chunk_size": 4096,
57+
"verbose": True,
58+
}
59+
)
60+
rag_node = RAGNode(
61+
input="user_prompt & (parsed_doc | doc)",
62+
output=["relevant_chunks"],
63+
node_config={
64+
"llm_model": llm_model,
65+
"embedder_model": embedder,
66+
"verbose": True,
67+
}
68+
)
69+
generate_answer_node = GenerateAnswerNode(
70+
input="user_prompt & (relevant_chunks | parsed_doc | doc)",
71+
output=["answer"],
72+
node_config={
73+
"llm_model": llm_model,
74+
"verbose": True,
75+
}
76+
)
77+
78+
# ************************************************
79+
# Create the graph by defining the connections
80+
# ************************************************
81+
82+
graph = BaseGraph(
83+
nodes=[
84+
robot_node,
85+
fetch_node,
86+
parse_node,
87+
rag_node,
88+
generate_answer_node,
89+
],
90+
edges=[
91+
(robot_node, fetch_node),
92+
(fetch_node, parse_node),
93+
(parse_node, rag_node),
94+
(rag_node, generate_answer_node)
95+
],
96+
entry_point=robot_node
97+
)
98+
99+
# ************************************************
100+
# Execute the graph
101+
# ************************************************
102+
103+
result, execution_info = graph.execute({
104+
"user_prompt": "Describe the content",
105+
"url": "https://example.com/"
106+
})
107+
108+
# get the answer from the result
109+
result = result.get("answer", "No answer found.")
110+
print(result)

‎examples/anthropic/inputs/books.xml

Lines changed: 120 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,120 @@
1+
<?xml version="1.0"?>
2+
<catalog>
3+
<book id="bk101">
4+
<author>Gambardella, Matthew</author>
5+
<title>XML Developer's Guide</title>
6+
<genre>Computer</genre>
7+
<price>44.95</price>
8+
<publish_date>2000-10-01</publish_date>
9+
<description>An in-depth look at creating applications
10+
with XML.</description>
11+
</book>
12+
<book id="bk102">
13+
<author>Ralls, Kim</author>
14+
<title>Midnight Rain</title>
15+
<genre>Fantasy</genre>
16+
<price>5.95</price>
17+
<publish_date>2000-12-16</publish_date>
18+
<description>A former architect battles corporate zombies,
19+
an evil sorceress, and her own childhood to become queen
20+
of the world.</description>
21+
</book>
22+
<book id="bk103">
23+
<author>Corets, Eva</author>
24+
<title>Maeve Ascendant</title>
25+
<genre>Fantasy</genre>
26+
<price>5.95</price>
27+
<publish_date>2000-11-17</publish_date>
28+
<description>After the collapse of a nanotechnology
29+
society in England, the young survivors lay the
30+
foundation for a new society.</description>
31+
</book>
32+
<book id="bk104">
33+
<author>Corets, Eva</author>
34+
<title>Oberon's Legacy</title>
35+
<genre>Fantasy</genre>
36+
<price>5.95</price>
37+
<publish_date>2001-03-10</publish_date>
38+
<description>In post-apocalypse England, the mysterious
39+
agent known only as Oberon helps to create a new life
40+
for the inhabitants of London. Sequel to Maeve
41+
Ascendant.</description>
42+
</book>
43+
<book id="bk105">
44+
<author>Corets, Eva</author>
45+
<title>The Sundered Grail</title>
46+
<genre>Fantasy</genre>
47+
<price>5.95</price>
48+
<publish_date>2001-09-10</publish_date>
49+
<description>The two daughters of Maeve, half-sisters,
50+
battle one another for control of England. Sequel to
51+
Oberon's Legacy.</description>
52+
</book>
53+
<book id="bk106">
54+
<author>Randall, Cynthia</author>
55+
<title>Lover Birds</title>
56+
<genre>Romance</genre>
57+
<price>4.95</price>
58+
<publish_date>2000-09-02</publish_date>
59+
<description>When Carla meets Paul at an ornithology
60+
conference, tempers fly as feathers get ruffled.</description>
61+
</book>
62+
<book id="bk107">
63+
<author>Thurman, Paula</author>
64+
<title>Splish Splash</title>
65+
<genre>Romance</genre>
66+
<price>4.95</price>
67+
<publish_date>2000-11-02</publish_date>
68+
<description>A deep sea diver finds true love twenty
69+
thousand leagues beneath the sea.</description>
70+
</book>
71+
<book id="bk108">
72+
<author>Knorr, Stefan</author>
73+
<title>Creepy Crawlies</title>
74+
<genre>Horror</genre>
75+
<price>4.95</price>
76+
<publish_date>2000-12-06</publish_date>
77+
<description>An anthology of horror stories about roaches,
78+
centipedes, scorpions and other insects.</description>
79+
</book>
80+
<book id="bk109">
81+
<author>Kress, Peter</author>
82+
<title>Paradox Lost</title>
83+
<genre>Science Fiction</genre>
84+
<price>6.95</price>
85+
<publish_date>2000-11-02</publish_date>
86+
<description>After an inadvertant trip through a Heisenberg
87+
Uncertainty Device, James Salway discovers the problems
88+
of being quantum.</description>
89+
</book>
90+
<book id="bk110">
91+
<author>O'Brien, Tim</author>
92+
<title>Microsoft .NET: The Programming Bible</title>
93+
<genre>Computer</genre>
94+
<price>36.95</price>
95+
<publish_date>2000-12-09</publish_date>
96+
<description>Microsoft's .NET initiative is explored in
97+
detail in this deep programmer's reference.</description>
98+
</book>
99+
<book id="bk111">
100+
<author>O'Brien, Tim</author>
101+
<title>MSXML3: A Comprehensive Guide</title>
102+
<genre>Computer</genre>
103+
<price>36.95</price>
104+
<publish_date>2000-12-01</publish_date>
105+
<description>The Microsoft MSXML3 parser is covered in
106+
detail, with attention to XML DOM interfaces, XSLT processing,
107+
SAX and more.</description>
108+
</book>
109+
<book id="bk112">
110+
<author>Galos, Mike</author>
111+
<title>Visual Studio 7: A Comprehensive Guide</title>
112+
<genre>Computer</genre>
113+
<price>49.95</price>
114+
<publish_date>2001-04-16</publish_date>
115+
<description>Microsoft Visual Studio 7 is explored in depth,
116+
looking at how Visual Basic, Visual C++, C#, and ASP+ are
117+
integrated into a comprehensive development
118+
environment.</description>
119+
</book>
120+
</catalog>

0 commit comments

Comments
 (0)