Compare commits

..

No commits in common. "master" and "CREWAI-integration" have entirely different histories.

2 changed files with 8 additions and 27 deletions

View File

@ -17,19 +17,14 @@ journalist draft is chunked, embedded, and stored in a collection; the editor
receives the top-N most relevant chunks as context.
"""
from __future__ import annotations
import json
import os
import random
import re
import string
from datetime import datetime
from typing import TYPE_CHECKING
if TYPE_CHECKING:
import chromadb # noqa: F811
import chromadb
from crewai.flow.flow import Flow, listen, start
from ollama import Client
from pydantic import BaseModel, ConfigDict
@ -90,21 +85,7 @@ class BlogFlow(Flow[BlogFlowState]):
)
@staticmethod
def _get_chroma_client() -> "chromadb.HttpClient":
# Lazily import chromadb here rather than at module level.
# chromadb unconditionally loads hnswlib (a native C++ library
# compiled with AVX instructions) even when using HttpClient
# to talk to an external ChromaDB server. Deferring the import
# avoids "Illegal instruction" (SIGILL) crashes in environments
# that lack AVX support (e.g. act, older CI runners).
try:
import chromadb
except ImportError as exc:
raise RuntimeError(
"chromadb is required for the editor phase but could not be "
f"imported: {exc}"
) from exc
def _get_chroma_client() -> chromadb.HttpClient:
chroma_port = int(os.environ["CHROMA_PORT"])
return chromadb.HttpClient(host=os.environ["CHROMA_HOST"], port=chroma_port)
@ -146,7 +127,7 @@ class BlogFlow(Flow[BlogFlowState]):
print(f"Error generating embeddings: {exc}")
return []
def _load_drafts_to_vector_db(self, drafts: list[str]) -> "chromadb.Collection":
def _load_drafts_to_vector_db(self, drafts: list[str]) -> chromadb.Collection:
"""Load journalist drafts into a new ChromaDB collection and return it."""
chroma = self._get_chroma_client()
collection_name = (
@ -184,7 +165,7 @@ class BlogFlow(Flow[BlogFlowState]):
return collection
@staticmethod
def _query_vector_db(collection: "chromadb.Collection", query_text: str) -> str:
def _query_vector_db(collection: chromadb.Collection, query_text: str) -> str:
"""Query the ChromaDB collection and return the most relevant
document chunks joined as a single string."""
ollama_client = BlogFlow._get_ollama_client()

View File

@ -42,7 +42,7 @@ class GitRepository:
print(f"Cloning failed: {e}")
return False
def fetch(self, remote_name="origin", ref_name="master"):
def fetch(self, remote_name="origin", ref_name="main"):
"""Fetch updates from a remote repository with authentication"""
try:
self.repo.remotes[remote_name].fetch(ref_name=ref_name)
@ -51,7 +51,7 @@ class GitRepository:
print(f"Fetching failed: {e}")
return False
def pull(self, remote_name="origin", ref_name="master"):
def pull(self, remote_name="origin", ref_name="main"):
"""Pull updates from a remote repository with authentication"""
print("Pulling Latest Updates (if any)")
try:
@ -93,8 +93,8 @@ class GitRepository:
self.repo.git.checkout(title)
self.pull(ref_name=title)
else:
# New branch, create from master
self.repo.git.checkout("-b", title, "origin/master")
# New branch, create from main
self.repo.git.checkout("-b", title, "origin/main")
# Ensure destination directory exists
dest_dir = f"{self.repo_path}src/content/"