-
-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #700 from ScrapeGraphAI/temp-1
Pre/beta
- Loading branch information
Showing
60 changed files
with
2,566 additions
and
202 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,60 @@ | ||
| """ | ||
| Basic example of scraping pipeline using Code Generator with schema | ||
| """ | ||
|
|
||
| import os, json | ||
| from typing import List | ||
| from dotenv import load_dotenv | ||
| from pydantic import BaseModel, Field | ||
| from scrapegraphai.graphs import CodeGeneratorGraph | ||
|
|
||
| load_dotenv() | ||
|
|
||
| # ************************************************ | ||
| # Define the output schema for the graph | ||
| # ************************************************ | ||
|
|
||
| class Project(BaseModel): | ||
| title: str = Field(description="The title of the project") | ||
| description: str = Field(description="The description of the project") | ||
|
|
||
| class Projects(BaseModel): | ||
| projects: List[Project] | ||
|
|
||
| # ************************************************ | ||
| # Define the configuration for the graph | ||
| # ************************************************ | ||
|
|
||
| anthropic_key = os.getenv("ANTHROPIC_API_KEY") | ||
|
|
||
| graph_config = { | ||
| "llm": { | ||
| "api_key":anthropic_key, | ||
| "model": "anthropic/claude-3-haiku-20240307", | ||
| }, | ||
| "verbose": True, | ||
| "headless": False, | ||
| "reduction": 2, | ||
| "max_iterations": { | ||
| "overall": 10, | ||
| "syntax": 3, | ||
| "execution": 3, | ||
| "validation": 3, | ||
| "semantic": 3 | ||
| }, | ||
| "output_file_name": "extracted_data.py" | ||
| } | ||
|
|
||
| # ************************************************ | ||
| # Create the SmartScraperGraph instance and run it | ||
| # ************************************************ | ||
|
|
||
| code_generator_graph = CodeGeneratorGraph( | ||
| prompt="List me all the projects with their description", | ||
| source="https://perinim.github.io/projects/", | ||
| schema=Projects, | ||
| config=graph_config | ||
| ) | ||
|
|
||
| result = code_generator_graph.run() | ||
| print(result) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,58 @@ | ||
| """ | ||
| Basic example of scraping pipeline using Code Generator with schema | ||
| """ | ||
|
|
||
| import os, json | ||
| from typing import List | ||
| from dotenv import load_dotenv | ||
| from pydantic import BaseModel, Field | ||
| from scrapegraphai.graphs import CodeGeneratorGraph | ||
|
|
||
| load_dotenv() | ||
|
|
||
| # ************************************************ | ||
| # Define the output schema for the graph | ||
| # ************************************************ | ||
|
|
||
| class Project(BaseModel): | ||
| title: str = Field(description="The title of the project") | ||
| description: str = Field(description="The description of the project") | ||
|
|
||
| class Projects(BaseModel): | ||
| projects: List[Project] | ||
|
|
||
| # ************************************************ | ||
| # Define the configuration for the graph | ||
| # ************************************************ | ||
|
|
||
| graph_config = { | ||
| "llm": { | ||
| "api_key": os.environ["AZURE_OPENAI_KEY"], | ||
| "model": "azure_openai/gpt-3.5-turbo", | ||
| }, | ||
| "verbose": True, | ||
| "headless": False, | ||
| "reduction": 2, | ||
| "max_iterations": { | ||
| "overall": 10, | ||
| "syntax": 3, | ||
| "execution": 3, | ||
| "validation": 3, | ||
| "semantic": 3 | ||
| }, | ||
| "output_file_name": "extracted_data.py" | ||
| } | ||
|
|
||
| # ************************************************ | ||
| # Create the SmartScraperGraph instance and run it | ||
| # ************************************************ | ||
|
|
||
| code_generator_graph = CodeGeneratorGraph( | ||
| prompt="List me all the projects with their description", | ||
| source="https://perinim.github.io/projects/", | ||
| schema=Projects, | ||
| config=graph_config | ||
| ) | ||
|
|
||
| result = code_generator_graph.run() | ||
| print(result) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,60 @@ | ||
| """ | ||
| Basic example of scraping pipeline using Code Generator with schema | ||
| """ | ||
|
|
||
| import os, json | ||
| from typing import List | ||
| from dotenv import load_dotenv | ||
| from pydantic import BaseModel, Field | ||
| from scrapegraphai.graphs import CodeGeneratorGraph | ||
|
|
||
| load_dotenv() | ||
|
|
||
| # ************************************************ | ||
| # Define the output schema for the graph | ||
| # ************************************************ | ||
|
|
||
| class Project(BaseModel): | ||
| title: str = Field(description="The title of the project") | ||
| description: str = Field(description="The description of the project") | ||
|
|
||
| class Projects(BaseModel): | ||
| projects: List[Project] | ||
|
|
||
| # ************************************************ | ||
| # Define the configuration for the graph | ||
| # ************************************************ | ||
|
|
||
|
|
||
| graph_config = { | ||
| "llm": { | ||
| "client": "client_name", | ||
| "model": "bedrock/anthropic.claude-3-sonnet-20240229-v1:0", | ||
| "temperature": 0.0 | ||
| }, | ||
| "verbose": True, | ||
| "headless": False, | ||
| "reduction": 2, | ||
| "max_iterations": { | ||
| "overall": 10, | ||
| "syntax": 3, | ||
| "execution": 3, | ||
| "validation": 3, | ||
| "semantic": 3 | ||
| }, | ||
| "output_file_name": "extracted_data.py" | ||
| } | ||
|
|
||
| # ************************************************ | ||
| # Create the SmartScraperGraph instance and run it | ||
| # ************************************************ | ||
|
|
||
| code_generator_graph = CodeGeneratorGraph( | ||
| prompt="List me all the projects with their description", | ||
| source="https://perinim.github.io/projects/", | ||
| schema=Projects, | ||
| config=graph_config | ||
| ) | ||
|
|
||
| result = code_generator_graph.run() | ||
| print(result) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,60 @@ | ||
| """ | ||
| Basic example of scraping pipeline using Code Generator with schema | ||
| """ | ||
|
|
||
| import os, json | ||
| from typing import List | ||
| from dotenv import load_dotenv | ||
| from pydantic import BaseModel, Field | ||
| from scrapegraphai.graphs import CodeGeneratorGraph | ||
|
|
||
| load_dotenv() | ||
|
|
||
| # ************************************************ | ||
| # Define the output schema for the graph | ||
| # ************************************************ | ||
|
|
||
| class Project(BaseModel): | ||
| title: str = Field(description="The title of the project") | ||
| description: str = Field(description="The description of the project") | ||
|
|
||
| class Projects(BaseModel): | ||
| projects: List[Project] | ||
|
|
||
| # ************************************************ | ||
| # Define the configuration for the graph | ||
| # ************************************************ | ||
|
|
||
| deepseek_key = os.getenv("DEEPSEEK_APIKEY") | ||
|
|
||
| graph_config = { | ||
| "llm": { | ||
| "model": "deepseek/deepseek-chat", | ||
| "api_key": deepseek_key, | ||
| }, | ||
| "verbose": True, | ||
| "headless": False, | ||
| "reduction": 2, | ||
| "max_iterations": { | ||
| "overall": 10, | ||
| "syntax": 3, | ||
| "execution": 3, | ||
| "validation": 3, | ||
| "semantic": 3 | ||
| }, | ||
| "output_file_name": "extracted_data.py" | ||
| } | ||
|
|
||
| # ************************************************ | ||
| # Create the SmartScraperGraph instance and run it | ||
| # ************************************************ | ||
|
|
||
| code_generator_graph = CodeGeneratorGraph( | ||
| prompt="List me all the projects with their description", | ||
| source="https://perinim.github.io/projects/", | ||
| schema=Projects, | ||
| config=graph_config | ||
| ) | ||
|
|
||
| result = code_generator_graph.run() | ||
| print(result) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,62 @@ | ||
| """ | ||
| Basic example of scraping pipeline using Code Generator with schema | ||
| """ | ||
|
|
||
| import os, json | ||
| from typing import List | ||
| from dotenv import load_dotenv | ||
| from pydantic import BaseModel, Field | ||
| from scrapegraphai.graphs import CodeGeneratorGraph | ||
|
|
||
| load_dotenv() | ||
|
|
||
| # ************************************************ | ||
| # Define the output schema for the graph | ||
| # ************************************************ | ||
|
|
||
| class Project(BaseModel): | ||
| title: str = Field(description="The title of the project") | ||
| description: str = Field(description="The description of the project") | ||
|
|
||
| class Projects(BaseModel): | ||
| projects: List[Project] | ||
|
|
||
| # ************************************************ | ||
| # Define the configuration for the graph | ||
| # ************************************************ | ||
|
|
||
| openai_key = os.getenv("OPENAI_APIKEY") | ||
|
|
||
| graph_config = { | ||
| "llm": { | ||
| "model": "ernie/ernie-bot-turbo", | ||
| "ernie_client_id": "<ernie_client_id>", | ||
| "ernie_client_secret": "<ernie_client_secret>", | ||
| "temperature": 0.1 | ||
| }, | ||
| "verbose": True, | ||
| "headless": False, | ||
| "reduction": 2, | ||
| "max_iterations": { | ||
| "overall": 10, | ||
| "syntax": 3, | ||
| "execution": 3, | ||
| "validation": 3, | ||
| "semantic": 3 | ||
| }, | ||
| "output_file_name": "extracted_data.py" | ||
| } | ||
|
|
||
| # ************************************************ | ||
| # Create the SmartScraperGraph instance and run it | ||
| # ************************************************ | ||
|
|
||
| code_generator_graph = CodeGeneratorGraph( | ||
| prompt="List me all the projects with their description", | ||
| source="https://perinim.github.io/projects/", | ||
| schema=Projects, | ||
| config=graph_config | ||
| ) | ||
|
|
||
| result = code_generator_graph.run() | ||
| print(result) |
Oops, something went wrong.