Use DaoXE in AnythingLLM

AnythingLLM's LLM Provider → OpenAI (Generic) takes a base URL, a key, and a model — the exact shape of DaoXE. Configure it once and document chat, agents and embedding-driven workflows all draw from one account (cheapest APIs guide).

Why route AnythingLLM through DaoXE#

• Your docs become a knowledge base. RAG chat over PDFs and notes with the model of your choice.
• One key, many vendors. Swap the backend without re-uploading or re-indexing anything.
• Explicit token controls. Context-window and max-token fields are first-class settings, not hidden defaults.

Set it up in AnythingLLM#

1. Open LLM settings. Settings → AI Providers → LLM → choose OpenAI (Generic) from the cloud providers.
2. Set the Base URL. Enter https://daoxe.com/v1 — the OpenAI SDK beneath it appends paths itself, so the URL must end at /v1.
3. Add key, pick model. Paste your DaoXE key; the Chat Model field lists IDs from your account's /v1/models — pick an exact one.
4. Size the two token fields. Model context window should match the real window of the chosen model; Max Tokens caps each request. Wrong values cause silent truncation, not errors.

Verify you actually get the model#

Prove the endpoint works before blaming the client — if this fails, no setting will fix it:

export DAOXE_API_KEY="your_api_key"

# List the exact model IDs your account can call
curl --fail-with-body --show-error --silent \
  https://daoxe.com/v1/models \
  -H "Authorization: Bearer ${DAOXE_API_KEY}"

Prove the endpoint outside the client, then diff a hard prompt against the official API at temperature 0:

curl --fail-with-body --show-error --silent \
  https://daoxe.com/v1/chat/completions \
  -H "Authorization: Bearer ${DAOXE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_EXACT_MODEL_ID",
    "max_tokens": 64,
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

Frequently asked questions#