.env.template

# This is a template for the .env file. Copy this file to .env and fill in the values for your accounts.

# ---- Cosmos DB ----
COSMOS_DB_ENDPOINT=https://<your-account>.documents.azure.com:443/
# COSMOS_DB__accountEndpoint is required for the Azure Functions change feed trigger
# (identity-based connection). Set it to the same value as COSMOS_DB_ENDPOINT.
COSMOS_DB__accountEndpoint=https://<your-account>.documents.azure.com:443/
# Optional fallback when Cosmos control-plane RBAC is unavailable (private preview).
# When set, the SDK uses the key for both data plane and control plane operations,
# letting you create databases/containers without RBAC role assignments.
# Leave blank to use DefaultAzureCredential / managed identity.
COSMOS_DB_KEY=
# Database name. Must match what the Function App reads (COSMOS_DB_DATABASE there).
# Default is "ai_memory"; change only if your infra deploys a different name.
COSMOS_DB_DATABASE=ai_memory
COSMOS_DB_MEMORIES_CONTAINER="memories"
COSMOS_DB_SUMMARIES_CONTAINER="memories_summaries"
COSMOS_DB_TURNS_CONTAINER="memories_turns"
COSMOS_DB_COUNTERS_CONTAINER=counter
COSMOS_DB_LEASE_CONTAINER=leases
# Throughput mode for all required Cosmos DB containers created by the toolkit
# (memories, counter, and lease).
# - serverless: default. The toolkit does not send container RU/s settings.
#   Use this only with a Cosmos DB account configured for serverless.
# - autoscale: the toolkit provisions all required containers with autoscale
#   throughput using COSMOS_DB_AUTOSCALE_MAX_RU as the max RU/s cap.
#   Default max RU/s is 1000.
COSMOS_DB_THROUGHPUT_MODE=serverless
COSMOS_DB_AUTOSCALE_MAX_RU=1000

# ---- Processing thresholds (set to 0 to disable) ----
THREAD_SUMMARY_EVERY_N=10
FACT_EXTRACTION_EVERY_N=1
USER_SUMMARY_EVERY_N=20

# ---- Processor ownership (in-process SDK vs. Function App / Durable) ----
# Controls which side runs the auto-trigger to avoid double-firing when both
# the SDK and the Function App are deployed against the same database.
#
#   * Unset / blank        -> SDK auto-trigger fires; FA change-feed SKIPS.
#                             (Pure SDK deployments — no env config needed.)
#   * "inprocess"          -> SDK auto-trigger fires; FA change-feed SKIPS.
#   * "durable"            -> SDK auto-trigger SKIPS; FA change-feed fires.
#
# The contract is asymmetric by design: the FA defaults to skip (default-deny)
# so a fresh FA deploy next to an existing SDK install does not race. If you
# run the Function App, you MUST set this to "durable" or processing will
# silently no-op.
MEMORY_PROCESSOR_OWNER=

# ---- AI Foundry / Azure OpenAI ----
# Use the account-level inference endpoint. Both of these forms work:
#   https://<your-account>.services.ai.azure.com
#   https://<your-account>.openai.azure.com
# A project-scoped Foundry URL (".../api/projects/<name>") is also accepted and
# automatically normalized to the inference base.
AI_FOUNDRY_ENDPOINT=https://<your-account>.openai.azure.com/
AI_FOUNDRY_API_KEY=
AI_FOUNDRY_EMBEDDING_DEPLOYMENT_NAME=text-embedding-3-large
AI_FOUNDRY_EMBEDDING_DIMENSIONS=1536
AI_FOUNDRY_EMBEDDING_DATA_TYPE=float32
AI_FOUNDRY_EMBEDDING_DISTANCE_FUNCTION=cosine
# Optional. Vector index type for the memories container: quantizedFlat
# (default), diskANN, or flat. quantizedFlat works on any Cosmos DB account
# (including the classic emulator); diskANN requires the DiskANN capability on
# the Cosmos DB account, so opt into it explicitly when available.
AI_FOUNDRY_EMBEDDING_VECTOR_INDEX_TYPE=quantizedFlat
COSMOS_DB_FULL_TEXT_LANGUAGE=en-US

# Embed raw conversation turns on write so they can be vector-searched via
# search_turns(). The turns container is always provisioned with a
# vector index, so toggling this never requires recreating the container.
ENABLE_TURN_EMBEDDINGS=false

AI_FOUNDRY_CHAT_DEPLOYMENT_NAME=<your-model-deployment>
# Optional. Pin the Azure OpenAI REST API version used by chat and embeddings
# clients. Leave blank to use the toolkit default ("2024-12-01-preview").
AZURE_OPENAI_API_VERSION=