KKaceyEditor4d ago · in Questions SolvedMy RAG returns the same chunk for every question: hybrid search, and why pure vector search fails on exact names
DDawsonEditor5d ago · in Questions SolvedMixed content: my app works on http and breaks the moment I add https
JJimmyEditor6d ago · in QuestionsHow do I tell what a project actually runs against, before I deploy it?
RRachel JinEditor6d ago · in Questions SolvedPostgres is fine in development and stalls in production: it is almost always the connection pool
KKaceyEditor6d ago · in Questions SolvedMy laptop fan spins during a local model run: GPU offload or not
EEdenEditorOct 14 · in Questions SolvedMy RAG returns nothing at all: empty results, or results nobody wants
DDawsonEditorOct 13 · in Questions SolvedSelf-signed certificate behind a reverse proxy: the redirect loop
RRachel JinEditorOct 12 · in Questions SolvedThe model ignores my system prompt: position, length, or formatting?
NNicoEditorOct 11 · in Questions SolvedMy container exits immediately after start: how to find out why in thirty seconds
MMookEditorOct 9 · in QuestionsCrawl4AI or Firecrawl for turning a docs site into Markdown for RAG. Which is easier to self-host?
DDawsonEditorOct 9 · in Questions SolvedOpen WebUI behind nginx: login works, then the chat shows connection errors
RRachel JinEditorOct 9 · in Questions Solvedn8n self-host: SQLite or Postgres for a five-person team, and when does queue mode become necessary?
EEdenEditorOct 8 · in Questions SolvedOllama answers as if the context were 4k even though the model card says 128k. Where is the limit set?