Lama index integration

.gitignore

@@ -0,0 +1,3 @@
+.env
+.DS_Store
+*.csv

cookbook/company-info/.env.example

@@ -0,0 +1 @@
+SGAI_API_KEY="your-api-key-here"

cookbook/github-trending/.env.example

@@ -0,0 +1 @@
+SGAI_API_KEY="your-api-key-here"

cookbook/homes-forsale/.env.example

@@ -0,0 +1 @@
+SGAI_API_KEY="your-api-key-here"

cookbook/wired-news/.env.example

@@ -0,0 +1 @@
+SGAI_API_KEY="your-api-key-here"

scrapegraph-py/cookbook/github-trending/a.py

@@ -0,0 +1,39 @@
+from llama_index.tools.scrapegraph.base import ScrapegraphToolSpec
+from pydantic import BaseModel, Field
+from typing import List
+import os
+
+# Initialize the ScrapegraphToolSpec
+scrapegraph_tool = ScrapegraphToolSpec()
+
+# Define the schema for a single repository
+class RepositorySchema(BaseModel):
+    name: str = Field(description="Name of the repository (e.g., 'owner/repo')")
+    description: str = Field(description="Description of the repository")
+    stars: int = Field(description="Star count of the repository")
+    forks: int = Field(description="Fork count of the repository")
+    today_stars: int = Field(description="Stars gained today")
+    language: str = Field(description="Programming language used")
+
+# Define the schema for a list of repositories
+class ListRepositoriesSchema(BaseModel):
+    repositories: List[RepositorySchema] = Field(description="List of GitHub trending repositories")
+
+# Make the API call to scrape GitHub trending repositories
+response = scrapegraph_tool.scrapegraph_smartscraper(
+    prompt="Extract information about trending GitHub repositories",
+    url="https://github.com/trending",
+    api_key="sgai-cd497c94-9ac5-4259-b7b5-f3283affe481",
+    schema=ListRepositoriesSchema,
+)
+
+# Get the result and print each repository
+result = response["result"]
+print("\nTrending Repositories:")
+for repo in result["repositories"]:
+    print(f"\nRepository: {repo['name']}")
+    print(f"Description: {repo['description']}")
+    print(f"Stars: {repo['stars']}")
+    print(f"Forks: {repo['forks']}")
+    print(f"Today's Stars: {repo['today_stars']}")
+    print(f"Language: {repo['language']}")

scrapegraph-py/cookbook/trial.py

@@ -0,0 +1,26 @@
+
+from llama_index.tools.scrapegraph.base import ScrapegraphToolSpec 
+
+scrapegraph_tool = ScrapegraphToolSpec() 
+
+from pydantic import BaseModel, Field 
+
+class FounderSchema(BaseModel): 
+    name: str = Field(description="Name of the founder") 
+    role: str = Field(description="Role of the founder") 
+    social_media: str = Field(description="Social media URL of the founder") 
+
+class ListFoundersSchema(BaseModel): 
+    founders: list[FounderSchema] = Field(description="List of founders") 
+
+response = scrapegraph_tool.scrapegraph_smartscraper( 
+    prompt="Extract product information", 
+    url="https://scrapegraphai.com/", 
+    api_key="sgai-cd497c94-9ac5-4259-b7b5-f3283affe481", 
+    schema=ListFoundersSchema, 
+) 
+
+result = response["result"] 
+
+for founder in result["founders"]: 
+    print(founder)

scrapegraph-py/cookbook/wired-news/a.py

@@ -0,0 +1,41 @@
+from llama_index.tools.scrapegraph.base import ScrapegraphToolSpec
+from pydantic import BaseModel, Field
+from typing import List
+import os
+
+# Initialize the ScrapegraphToolSpec
+scrapegraph_tool = ScrapegraphToolSpec()
+
+# Schema for a single news item
+class NewsItemSchema(BaseModel):
+    category: str = Field(description="Category of the news (e.g., 'Health', 'Environment')")
+    title: str = Field(description="Title of the news article")
+    link: str = Field(description="URL to the news article")
+    author: str = Field(description="Author of the news article")
+
+# Schema containing a list of news items
+class ListNewsSchema(BaseModel):
+    news: List[NewsItemSchema] = Field(description="List of news articles with their details")
+
+# Make the API call to scrape news articles
+response = scrapegraph_tool.scrapegraph_smartscraper(
+    prompt="Extract information about science news articles",
+    url="https://www.wired.com/tag/science/",
+    api_key="sgai-cd497c94-9ac5-4259-b7b5-f3283affe481",
+    schema=ListNewsSchema,
+)
+
+# Get the result and print each news article
+result = response["result"]
+print("\nWired Science News Articles:")
+for article in result["news"]:
+    print(f"\nCategory: {article['category']}")
+    print(f"Title: {article['title']}")
+    print(f"Author: {article['author']}")
+    print(f"Link: {article['link']}")
+
+# Save to CSV (optional)
+import pandas as pd
+df = pd.DataFrame(result["news"])
+df.to_csv("wired_news.csv", index=False)
+print("\nData saved to wired_news.csv")