PdfPlumber Loader

pip install "upsonic[loaders]"

pip install rapidocr-onnxruntime

from upsonic import Agent, Task, KnowledgeBase
from upsonic.loaders import PdfPlumberLoader, PdfPlumberLoaderConfig
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.text_splitter import RecursiveChunker, RecursiveChunkingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

# Configure loader with table extraction
loader_config = PdfPlumberLoaderConfig(
    extraction_mode="hybrid",
    extract_tables=True,
    table_format="markdown"
)
loader = PdfPlumberLoader(loader_config)

# Setup KnowledgeBase
embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
chunker = RecursiveChunker(RecursiveChunkingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="pdf_tables",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.IN_MEMORY)
))

kb = KnowledgeBase(
    sources=["report.pdf"],
    embedding_provider=embedding,
    vectordb=vectordb,
    loaders=[loader],
    splitters=[chunker]
)

# Query with Agent
agent = Agent("openai/gpt-4o")
task = Task("Extract all table data", context=[kb])
result = agent.do(task)
print(result)