Add LLM chat integration with streaming responses via Ollama

Phase 4: Full chat system with SSE streaming, note-aware context, and
conversation persistence.

Backend:
- Migration 0005: conversations + messages tables with FKs and indexes
- Conversation/Message SQLAlchemy models with relationships
- LLM service: ensure_model (auto-pull on startup), stream_chat (NDJSON),
  generate_completion, fetch_url_content (HTML stripping), build_context
  (keyword extraction, related note search, URL content injection)
- Chat service: conversation CRUD, save_response_as_note,
  summarize_conversation_as_note
- Chat routes blueprint: 9 endpoints including SSE streaming for messages,
  save/summarize as note, Ollama model listing
- Auto-pull llama3.1 model on app startup (non-blocking)

Frontend:
- apiStreamPost: SSE client using fetch + ReadableStream
- Chat Pinia store with streaming state management
- ChatView: dedicated /chat page with conversation sidebar + message thread
- ChatPanel: slide-out panel with contextNoteId from current route
- ChatMessage: markdown-rendered message bubble with "Save as Note" action
- Updated AppHeader with Chat nav link + panel toggle button
- Updated App.vue to mount ChatPanel with route-derived context
- Added /chat and /chat/:id routes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-10 18:45:22 -05:00
parent 807cde30be
commit d2b8ab8fe8
19 changed files with 1906 additions and 35 deletions
+194
View File
@@ -0,0 +1,194 @@
import json
import logging
import re
from collections.abc import AsyncGenerator
import httpx
from fabledassistant.config import Config
from fabledassistant.services.notes import get_note, list_notes
logger = logging.getLogger(__name__)
STOP_WORDS = frozenset({
"a", "an", "the", "is", "it", "to", "in", "for", "of", "and", "or",
"on", "at", "by", "with", "from", "as", "be", "was", "were", "been",
"are", "am", "do", "does", "did", "have", "has", "had", "will", "would",
"can", "could", "shall", "should", "may", "might", "must", "that",
"this", "these", "those", "i", "me", "my", "you", "your", "he", "she",
"we", "they", "them", "his", "her", "its", "our", "their", "what",
"which", "who", "whom", "how", "when", "where", "why", "not", "no",
"but", "if", "so", "than", "too", "very", "just", "about", "up",
})
async def ensure_model(model: str) -> None:
"""Check if model exists in Ollama, pull if missing."""
try:
async with httpx.AsyncClient(timeout=10.0) as client:
resp = await client.get(f"{Config.OLLAMA_URL}/api/tags")
resp.raise_for_status()
data = resp.json()
names = {m["name"] for m in data.get("models", [])}
# Check both with and without :latest tag
if model in names or f"{model}:latest" in names:
logger.info("Model '%s' already available", model)
return
except Exception:
logger.warning("Failed to check Ollama models, attempting pull anyway")
logger.info("Pulling model '%s' from Ollama...", model)
try:
async with httpx.AsyncClient(timeout=600.0) as client:
async with client.stream(
"POST",
f"{Config.OLLAMA_URL}/api/pull",
json={"name": model},
) as resp:
resp.raise_for_status()
async for line in resp.aiter_lines():
if line.strip():
status = json.loads(line)
if "status" in status:
logger.info("Pull %s: %s", model, status["status"])
logger.info("Model '%s' pulled successfully", model)
except Exception:
logger.warning("Failed to pull model '%s' — chat may not work", model, exc_info=True)
async def stream_chat(
messages: list[dict], model: str
) -> AsyncGenerator[str, None]:
"""Stream chat completion from Ollama, yielding content chunks."""
async with httpx.AsyncClient(timeout=httpx.Timeout(300.0, connect=10.0)) as client:
async with client.stream(
"POST",
f"{Config.OLLAMA_URL}/api/chat",
json={"model": model, "messages": messages, "stream": True},
) as resp:
resp.raise_for_status()
async for line in resp.aiter_lines():
if not line.strip():
continue
data = json.loads(line)
chunk = data.get("message", {}).get("content", "")
if chunk:
yield chunk
if data.get("done"):
break
async def generate_completion(messages: list[dict], model: str) -> str:
"""Non-streaming chat completion, returns full response text."""
async with httpx.AsyncClient(timeout=httpx.Timeout(300.0, connect=10.0)) as client:
resp = await client.post(
f"{Config.OLLAMA_URL}/api/chat",
json={"model": model, "messages": messages, "stream": False},
)
resp.raise_for_status()
data = resp.json()
return data.get("message", {}).get("content", "")
async def fetch_url_content(url: str) -> str:
"""Fetch a URL and return text content (HTML tags stripped)."""
try:
async with httpx.AsyncClient(
timeout=15.0, follow_redirects=True, headers={"User-Agent": "FabledAssistant/1.0"}
) as client:
resp = await client.get(url)
resp.raise_for_status()
text = resp.text
# Strip HTML tags
text = re.sub(r"<script[^>]*>.*?</script>", "", text, flags=re.DOTALL)
text = re.sub(r"<style[^>]*>.*?</style>", "", text, flags=re.DOTALL)
text = re.sub(r"<[^>]+>", " ", text)
# Collapse whitespace
text = re.sub(r"\s+", " ", text).strip()
# Truncate to reasonable size
if len(text) > 4000:
text = text[:4000] + "..."
return text
except Exception as e:
logger.warning("Failed to fetch URL %s: %s", url, e)
return f"[Failed to fetch URL: {url}]"
def _extract_keywords(text: str) -> list[str]:
"""Extract meaningful keywords from text for note search."""
words = re.findall(r"\b[a-zA-Z]{3,}\b", text.lower())
keywords = [w for w in words if w not in STOP_WORDS]
# Deduplicate while preserving order
seen: set[str] = set()
unique = []
for w in keywords:
if w not in seen:
seen.add(w)
unique.append(w)
return unique[:5]
def _find_urls(text: str) -> list[str]:
"""Find URLs in text."""
return re.findall(r"https?://[^\s<>\"')\]]+", text)
async def build_context(
history: list[dict],
current_note_id: int | None,
user_message: str,
) -> list[dict]:
"""Build messages array for Ollama with system prompt and context."""
system_parts = [
"You are a helpful assistant integrated into a note-taking and task-tracking app called Fabled Assistant. "
"Help users with their notes, tasks, and general questions. "
"When note context is provided, use it to give relevant answers."
]
# Include current note context if provided
if current_note_id:
note = await get_note(current_note_id)
if note:
system_parts.append(
f"\n\n--- Current Note ---\n"
f"Title: {note.title}\n"
f"Content:\n{note.body}\n"
f"--- End Note ---"
)
# Search notes by keywords from user message
keywords = _extract_keywords(user_message)
if keywords:
search_q = " ".join(keywords[:3])
try:
notes, _ = await list_notes(q=search_q, limit=3)
if notes:
snippets = []
for n in notes:
# Skip the current note (already included)
if current_note_id and n.id == current_note_id:
continue
body_preview = n.body[:300] if n.body else ""
snippets.append(f"- {n.title}: {body_preview}")
if snippets:
system_parts.append(
"\n\n--- Related Notes ---\n"
+ "\n".join(snippets)
+ "\n--- End Related Notes ---"
)
except Exception:
pass
# Fetch URL content from user message
urls = _find_urls(user_message)
for url in urls[:2]: # Limit to 2 URLs
content = await fetch_url_content(url)
if content and not content.startswith("[Failed"):
system_parts.append(
f"\n\n--- Content from {url} ---\n{content}\n--- End URL Content ---"
)
messages = [{"role": "system", "content": "".join(system_parts)}]
messages.extend(history)
messages.append({"role": "user", "content": user_message})
return messages