script_generator_huggingfacehub

""" 
Basic example of scraping pipeline using ScriptCreatorGraph
"""

import os
from dotenv import load_dotenv
from scrapegraphai.graphs import ScriptCreatorGraph
from scrapegraphai.utils import prettify_exec_info
from langchain_community.llms import HuggingFaceEndpoint
from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings

load_dotenv()

# ************************************************
# Define the configuration for the graph
# ************************************************

HUGGINGFACEHUB_API_TOKEN = os.getenv('HUGGINGFACEHUB_API_TOKEN')
# ************************************************
# Initialize the model instances
# ************************************************

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"
)

# ************************************************
# Create the SmartScraperGraph instance and run it
# ************************************************

graph_config = {
    "llm": {"model_instance": llm_model_instance},
    "embeddings": {"model_instance": embedder_model_instance}
}
# ************************************************
# Create the ScriptCreatorGraph instance and run it
# ************************************************

script_creator_graph = ScriptCreatorGraph(
    prompt="List me all the projects with their description.",
    # also accepts a string with the already downloaded HTML code
    source="https://perinim.github.io/projects",
    config=graph_config
)

result = script_creator_graph.run()
print(result)

# ************************************************
# Get graph execution info
# ************************************************

graph_exec_info = script_creator_graph.get_execution_info()
print(prettify_exec_info(graph_exec_info))