| import json |
| import chromadb |
| from agentic_workflow.config import LLM_MODEL |
| from langchain_ollama import ChatOllama |
| import re |
| from langchain_core.messages import HumanMessage, SystemMessage |
|
|
| client = chromadb.PersistentClient(path="./chroma_db") |
| llm = ChatOllama(model=LLM_MODEL, temperature=0) |
|
|
| |
| def analyse_intent(query: str) -> dict: |
|
|
| system = """ |
| You are an intent classifier. Given a user query, return ONLY valid JSON with: |
| - "intent": one of "factual", "conversational", "follow_up", "sensitive" |
| - "needs_context": true if retrieval from a knowledge base is needed, false otherwise |
| - "needs_history": true if this looks like a follow-up to a prior turn, false otherwise |
| |
| Rules: |
| - Greetings / chit-chat → conversational, needs_context: false |
| - Questions about facts / documents → factual, needs_context: true |
| - "you said earlier" / pronouns like "it" / "that" → follow_up, needs_history: true |
| - Personal data, health, finance → sensitive |
| Return ONLY the JSON object. No explanation. |
| """ |
| |
| response = llm.invoke([ |
| SystemMessage(content=system), |
| HumanMessage(content=query) |
| ]) |
| raw = response.content.strip() |
| |
| raw = re.sub(r"^```(?:json)?\s*|\s*```$", "", raw).strip() |
|
|
| try: |
| parsed = json.loads(raw) |
| except json.JSONDecodeError: |
| parsed = {} |
|
|
| return { |
| "intent": "factual", |
| "needs_context": True, |
| "needs_history": False, |
| **parsed |
| } |
|
|
| |
| |
| |
| |
| |
| |
| |
| |
