Code Generator functionalities and graph

examples/anthropic/code_generator_graph_anthropic.py

@@ -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 langchain_core.pydantic_v1 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)

examples/azure/code_generator_graph_azure.py

@@ -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 langchain_core.pydantic_v1 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)

examples/bedrock/code_generator_graph_bedrock.py

@@ -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 langchain_core.pydantic_v1 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)

examples/deepseek/code_generator_graph_deepseek.py

@@ -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 langchain_core.pydantic_v1 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)

examples/ernie/code_generator_graph_ernie.py

@@ -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 langchain_core.pydantic_v1 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)

examples/fireworks/code_generator_graph_fireworks.py

@@ -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 langchain_core.pydantic_v1 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
+# ************************************************
+
+fireworks_api_key = os.getenv("FIREWORKS_APIKEY")
+
+graph_config = {
+    "llm": {
+        "api_key": fireworks_api_key,
+        "model": "fireworks/accounts/fireworks/models/mixtral-8x7b-instruct"
+    },
+    "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)