RAGWire Architecture and Setup

pip install ragwire

ollama pull qwen3.5:9b
ollama pull qwen3-embedding:0.6b

docker run -p 6333:6333 qdrant/qdrant

embeddings:
  provider: "ollama"
  model: "qwen3-embedding:0.6b"
  base_url: "http://localhost:11434"

llm:
  provider: "ollama"
  model: "qwen3.5:9b"
  base_url: "http://localhost:11434"
  num_ctx: 16384

vectorstore:
  url: "http://localhost:6333"
  collection_name: "finance-rag-ollama"
  use_sparse: true
  force_recreate: false

retriever:
  search_type: "hybrid"
  top_k: 5
  auto_filter: false

metadata:
  config_file: "finance_metadata.yaml"

loader:
  extensions: [".pdf", ".docx", ".xlsx", ".pptx", ".txt", ".md"]

splitter:
  chunk_size: 10000
  chunk_overlap: 2000
  strategy: "markdown"   # "markdown" | "recursive"

embeddings:
  provider: "ollama"
  model: "nomic-embed-text"
  base_url: "http://localhost:11434"

llm:
  provider: "ollama"
  model: "qwen3.5:9b"
  base_url: "http://localhost:11434"
  num_ctx: 65536

vectorstore:
  url: "http://localhost:6333"
  collection_name: "my_docs"
  use_sparse: true
  force_recreate: false

retriever:
  search_type: "hybrid"   # "similarity" | "mmr" | "hybrid"
  top_k: 5
  auto_filter: false

logging:
  level: "INFO"
  console_output: true
  colored: true

prompt: |
  You are parsing an SEC filing. This document IS an SEC filing — treat it as such.
  Extract the four fields below. All values must be lowercase strings.

  **company_name**: The company that filed this document.
  Scan for "registrant", the title block, or the company name printed above the form number.
  Use the full legal name. Example: "AMAZON.COM, INC." → 'amazon.com inc.'

  **doc_type**: The SEC form type. Map exactly:
  "Form 10-K" or "Annual Report on Form 10-K" → '10-k'
  "Form 10-Q" or "Quarterly Report on Form 10-Q" → '10-q'
  "Form 8-K" or "Current Report on Form 8-K" → '8-k'

  **fiscal_year**: The primary year this filing covers.
  Look for "fiscal year ended", "year ended", "for the year ended".
  Return a single 4-digit integer. Example: "Year ended December 31, 2024" → 2024

  **fiscal_quarter**: The quarter this filing covers. Only for 10-Q filings — null for 10-K and 8-K.
  Look for "quarter ended", "three months ended", or "Q1/Q2/Q3".
  Map: first/Q1 → 'q1', second/Q2 → 'q2', third/Q3 → 'q3', fourth/Q4 → 'q4'

  ## Grounding
  If existing collection values are provided above, reuse the exact stored value when this document refers to the same entity.

fields:
  - name: company_name
    description: "Full legal registrant name in lowercase. Example: 'alphabet inc.', 'apple inc.'"

  - name: doc_type
    description: "SEC form type: '10-k', '10-q', or '8-k'. Null if not an SEC filing."
    values: ["10-k", "10-q", "8-k"]

  - name: fiscal_year
    description: "Primary fiscal year as a 4-digit integer (e.g. 2024). Null if not stated."
    type: integer

  - name: fiscal_quarter
    description: "Fiscal quarter: 'q1', 'q2', 'q3', or 'q4'. Only for 10-Q. Null for 10-K and 8-K."
    values: ["q1", "q2", "q3", "q4"]

logger = setup_logging(log_level="INFO")

rag = RAGWire('config.yaml')

stats = rag.ingest_documents(["../data/finance_data/Apple_10k_2025.pdf"])

results = rag.retrieve("What is the apple's revenue?")

query = "what is apple's revenue in 2025?"
results = rag.retrieve(query=query, filters={'company_name': 'apple inc.'})

query = "what is revenue of Google in 2024?"
results = rag.retrieve(
    query=query,
    filters={'company_name': 'alphabet inc.', 'fiscal_year': 2024}
)

rag._auto_filter = True

query = "what is apple's revenue in 2025?"
results = rag.retrieve(query=query)

Auto-extracted filters from query: {'company_name': 'apple inc.', 'fiscal_year': 2025}

rag._auto_filter = False

from langchain.agents import create_agent
from langchain.tools import tool
from langchain.messages import HumanMessage
from langchain_ollama import ChatOllama
from langgraph.checkpoint.memory import InMemorySaver

@tool
def search_documents(query: str):
    """Search the document knowledge base for relevant information."""
    results = rag.retrieve(query=query)
    if not results:
        return "No relevant information is found!"
    else:
        return results

agent = create_agent(
    model=ChatOllama(model='qwen3.5:9b'),
    tools=[search_documents],
    system_prompt="You are a helpful document assistant. Use search_documents to answer questions.",
    checkpointer=InMemorySaver()
)

@tool
def get_filter_context(query: str) -> str:
    """Get available metadata fields, stored values, and filter suggestions for a query.

    Call this before search_documents when the query involves a specific company,
    year, or document type. Skip for purely semantic queries.
    """
    return rag.get_filter_context(query)

@tool
def search_documents(query: str, filters=None):
    """Search the document knowledge base for relevant information.

    Args:
        query: The search query
        filters: Optional metadata filters from get_filter_context.
    """
    results = rag.retrieve(query=query, filters=filters)
    if not results:
        return "No relevant information is found!"
    else:
        return results

agent = create_agent(
    model=ChatOllama(model='qwen3.5:9b'),
    tools=[get_filter_context, search_documents],
    system_prompt=(
        "You are a helpful financial document assistant. "
        "For complex questions, break them down into simple sub-questions. "
        "Always use search_documents to retrieve information — never answer from general knowledge. "
        "Use get_filter_context before search_documents when the query involves specific metadata. "
        "Always cite the source document in your answer."
    ),
    checkpointer=InMemorySaver(),
)

config = {"configurable": {"thread_id": "demo"}}

print("\nRAG Agent ready. Type 'quit' to exit.\n")

while True:
    question = input("You: ").strip()
    if question.lower() in ("quit", "exit", "q"):
        break
    if not question:
        continue
    response = agent.invoke(
        {"messages": [HumanMessage(question)]},
        config=config,
    )
    print(f"\nAgent: {response['messages'][-1].content}\n")