code_generator_graph_huggingfacehub

""" 
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
from langchain_community.llms import HuggingFaceEndpoint
from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings

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
# ************************************************

HUGGINGFACEHUB_API_TOKEN = os.getenv('HUGGINGFACEHUB_API_TOKEN')

repo_id = "mistralai/Mistral-7B-Instruct-v0.2"

llm_model_instance = HuggingFaceEndpoint(
    repo_id=repo_id, max_length=128, temperature=0.5, token=HUGGINGFACEHUB_API_TOKEN
)

embedder_model_instance = HuggingFaceInferenceAPIEmbeddings(
    api_key=HUGGINGFACEHUB_API_TOKEN, model_name="sentence-transformers/all-MiniLM-l6-v2"
)

graph_config = {
    "llm": {
        "model_instance": llm_model_instance
    },
    "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)