Indexed Processing

from upsonic import Agent, Task, KnowledgeBase
from upsonic.loaders.pdf import PdfLoader
from upsonic.loaders.config import PdfLoaderConfig
from upsonic.text_splitter.recursive import RecursiveChunker, RecursiveChunkingConfig
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="shared_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.IN_MEMORY)
))

loader = PdfLoader(PdfLoaderConfig())
splitter = RecursiveChunker(RecursiveChunkingConfig(chunk_size=512))

kb = KnowledgeBase(
    sources=["doc1.pdf", "doc2.pdf", "doc3.pdf"],
    embedding_provider=embedding,
    vectordb=vectordb,
    loaders=[loader],       # Single loader shared across all sources
    splitters=[splitter]    # Single splitter shared across all sources
)

agent = Agent("anthropic/claude-sonnet-4-5")
task = Task(
    description="List the safety precautions mentioned across all documents",
    context=[kb]
)

result = agent.do(task)
print(result)

from upsonic import Agent, Task, KnowledgeBase
from upsonic.loaders.pdf import PdfLoader
from upsonic.loaders.markdown import MarkdownLoader
from upsonic.loaders.config import PdfLoaderConfig, MarkdownLoaderConfig
from upsonic.text_splitter.recursive import RecursiveChunker, RecursiveChunkingConfig
from upsonic.text_splitter.semantic import SemanticChunker, SemanticChunkingConfig
from upsonic.embeddings import OpenAIEmbedding, OpenAIEmbeddingConfig
from upsonic.vectordb import ChromaProvider, ChromaConfig, ConnectionConfig, Mode

embedding = OpenAIEmbedding(OpenAIEmbeddingConfig())
vectordb = ChromaProvider(ChromaConfig(
    collection_name="indexed_kb",
    vector_size=1536,
    connection=ConnectionConfig(mode=Mode.IN_MEMORY)
))

# Index 0 → manual.pdf, Index 1 → guide.md
loaders = [
    PdfLoader(PdfLoaderConfig()),
    MarkdownLoader(MarkdownLoaderConfig())
]

# Index 0 → small chunks for precise PDF retrieval
# Index 1 → semantic chunking for Markdown prose
splitters = [
    RecursiveChunker(RecursiveChunkingConfig(chunk_size=512)),
    SemanticChunker(SemanticChunkingConfig(
        embedding_provider=embedding,
        chunk_size=1024
    ))
]

kb = KnowledgeBase(
    sources=["manual.pdf", "guide.md"],
    embedding_provider=embedding,
    vectordb=vectordb,
    loaders=loaders,
    splitters=splitters
)

agent = Agent("anthropic/claude-sonnet-4-5")
task = Task(
    description="What are the dependencies listed in the markdown guide versus the PDF manual?",
    context=[kb]
)

result = agent.do(task)
print(result)

sources:    ["manual.pdf",  "guide.md",  "data.csv"]
              ↓ index 0      ↓ index 1    ↓ index 2
loaders:    [PdfLoader,     MdLoader,    CsvLoader]
splitters:  [Recursive,     Semantic,    Recursive]