.env.example · aaronrene/knowtation

1

# Copy to .env and set your keys. Do not commit .env.

2

# OPENAI_API_KEY=sk-your-key-here

3

#

4

# ── Two LLM lanes (different keys / providers) ─────────────────────────────

5

# 1) EMBEDDINGS = Meaning search + indexer (vectors). NOT Anthropic — use Ollama,

6

# OpenAI, Voyage, or DeepInfra. Set in config/local.yaml embedding: { provider, model } and/or:

7

# EMBEDDING_PROVIDER=ollama|openai|voyage|deepinfra EMBEDDING_MODEL=...

8

# Voyage (cloud, non-OpenAI): EMBEDDING_PROVIDER=voyage + VOYAGE_API_KEY

9

# DeepInfra (single-key with chat above; OpenAI-compatible API):

10

# EMBEDDING_PROVIDER=deepinfra + DEEPINFRA_API_KEY

11

# EMBEDDING_MODEL=BAAI/bge-large-en-v1.5 # default; 1024-dim

12

# Other options: Qwen/Qwen3-Embedding-8B (4096), intfloat/multilingual-e5-large-instruct (1024)

13

# NOTE: Switching embedding provider OR dimension requires a vault re-index.

14

# 2) CHAT = proposal Enrich / review hints / completeChat.

15

# Provider order (lib/llm-complete.mjs):

16

# a) KNOWTATION_CHAT_PROVIDER=deepinfra → DeepInfra (Qwen/Llama/Mistral) with

17

# OpenAI/Anthropic fallback if their keys are also set. Single OpenAI-compatible bill;

18

# same DEEPINFRA_API_KEY also works for OpenClaw orchestration (image gen, embeddings, TTS).

19

# b) KNOWTATION_CHAT_PROVIDER=openai|anthropic → lock to that provider (no fallback).

20

# c) Implicit DeepInfra: DEEPINFRA_API_KEY set AND no OpenAI/Anthropic key → DeepInfra.

21

# d) Default: OpenAI → Anthropic → Ollama (unchanged for existing deploys).

22

# KNOWTATION_CHAT_PREFER_ANTHROPIC=1 flips OpenAI/Anthropic order when both are set.

23

# ANTHROPIC_API_KEY=

24

# ANTHROPIC_CHAT_MODEL=claude-3-5-haiku-20241022

25

# KNOWTATION_CHAT_PREFER_ANTHROPIC=1

26

# DEEPINFRA_API_KEY=

27

# DEEPINFRA_CHAT_MODEL=Qwen/Qwen2.5-72B-Instruct # default; cheaper hint model: meta-llama/Meta-Llama-3.1-8B-Instruct

28

# KNOWTATION_CHAT_PROVIDER=deepinfra # explicit lock; omit for default OpenAI-first behavior

29

# VOYAGE_API_KEY= # when embedding.provider is voyage (see docs/setup.md)

30

# Hub (Phase 11): required for npm run hub (self-hosted). See docs/TWO-PATHS-HOSTED-AND-SELF-HOSTED.md#quick-start-self-hosted

31

# HUB_JWT_SECRET=your-long-random-secret

32

# KNOWTATION_VAULT_PATH=/absolute/path/to/vault (or set in config/local.yaml)

33

#

34

# Gateway → canister authentication (required for production).

35

# Set a strong random secret (64+ hex chars), then call admin_set_gateway_auth_secret on the canister.

36

# CANISTER_AUTH_SECRET=

37

#

38

# Full operator export (all users; hub canister must have secret set — see docs/OPERATOR-BACKUP.md)

39

# KNOWTATION_OPERATOR_EXPORT_URL=https://<hub-canister-id>.icp0.io

40

# KNOWTATION_OPERATOR_EXPORT_KEY=long-random-secret-matching-admin_set_operator_export_secret

41

# KNOWTATION_OPERATOR_EXPORT_DIR=./backups

42

#

43

# Optional: before `dfx deploy hub --network ic`, `npm run canister:release-prep` can export vault(s) to ./backups/

44

# (same script as `npm run canister:export-backup` and scheduled HTTP vault export — see docs/DEPLOY-HOSTED.md §6)

45

# KNOWTATION_CANISTER_BACKUP_USER_ID=google:123

46

# KNOWTATION_CANISTER_URL=https://<canister-id>.icp0.io

47

# KNOWTATION_CANISTER_BACKUP_URL= # alias for CANISTER_URL (e.g. CI secret name)

48

# KNOWTATION_CANISTER_BACKUP_VAULT_ID=default

49

# KNOWTATION_CANISTER_BACKUP_VAULT_IDS=default,second # comma-separated; overrides VAULT_ID when set

50

# KNOWTATION_CANISTER_BACKUP_DIR=./backups

51

# KNOWTATION_CANISTER_BACKUP_ENCRYPT_KEY_HEX= # 64 hex chars → AES-256-GCM .json.enc output

52

# KNOWTATION_CANISTER_BACKUP_S3_BUCKET=

53

# KNOWTATION_CANISTER_BACKUP_S3_PREFIX=knowtation-canister-backups/

54

# KNOWTATION_CANISTER_BACKUP_SKIP_S3=1 # local: skip S3 even if bucket set

55

# AWS_ACCESS_KEY_ID= AWS_SECRET_ACCESS_KEY= AWS_REGION=us-east-1

56

#

57

# CLI / curl / repo scripts (verify-hosted-hub-api, seed:*, `knowtation propose`) read KNOWTATION_HUB_URL,

58

# KNOWTATION_HUB_TOKEN, KNOWTATION_HUB_VAULT_ID — not *_LOCAL / *_HOSTED. If you use suffixed names in .env,

59

# after `source .env` run exports, e.g. for hosted:

60

# export KNOWTATION_HUB_URL="$KNOWTATION_HUB_URL_HOSTED"

61

# export KNOWTATION_HUB_TOKEN="$KNOWTATION_HUB_TOKEN_HOSTED"

62

# export KNOWTATION_HUB_VAULT_ID="$KNOWTATION_HUB_VAULT_ID_HOSTED"

63

#

64

# Optional proposal LLM (exact names; env locks Settings → Backup checkboxes when set to 1/0 or true/false):

65

# KNOWTATION_HUB_PROPOSAL_REVIEW_HINTS=1

66

# KNOWTATION_HUB_PROPOSAL_ENRICH=1

67

#

68

# AIR Improvement D: built-in attestation endpoint (hosted gateway).

69

# When set (32+ chars), the gateway auto-configures KNOWTATION_AIR_ENDPOINT to its own

70

# /api/v1/attest route. All hosted note writes are then attested (HMAC-signed, stored in

71

# Netlify Blobs). Verify any attestation via GET /api/v1/attest/:id.

72

# ATTESTATION_SECRET=your-long-random-secret-min-32-chars

73

#

74

# Hosted memory consolidation (Session 10 / Stream 1 — bridge + gateway).

75

# CONSOLIDATION_LLM_API_KEY: LLM key for hosted consolidation passes; falls back to OPENAI_API_KEY.

76

# CONSOLIDATION_LLM_MODEL: Model to use (default: gpt-4o-mini).

77

# CONSOLIDATION_COST_CAP_USD: Optional daily spend cap per user on the bridge (no cap if unset).

78

# CONSOLIDATION_LLM_API_KEY=

79

# CONSOLIDATION_LLM_MODEL=gpt-4o-mini

80

# CONSOLIDATION_COST_CAP_USD=