WeKnora/docker-compose.dev.yml

589 lines
23 KiB
YAML
Raw Normal View History

# 开发环境配置 - 只启动基础设施服务,app 和 frontend 在本地运行
services:
# 只启动依赖的基础设施服务
postgres:
fix(deploy): bump paradedb image to v0.25.11-pg17 (#4120) * fix(deploy): bump paradedb image to v0.25.11-pg17 Batch-importing large knowledge bases on the pinned paradedb/paradedb:v0.22.6-pg17 image drives PostgreSQL into a PANIC/crash-recovery loop (corrupted page pointers in shared buffers, amcheck clean, no OOM), taking every ingest task down with it. Three independent fixes upstream cover this exact write path, and the pinned image predates all of them: - pgvector 0.8.2 fixed a buffer overflow in parallel HNSW index builds, 0.8.3 fixed possible index corruption during HNSW vacuuming, and 0.8.4 fixed inserts during HNSW vacuuming; the image ships pgvector 0.8.1, and the embeddings table maintains three HNSW halfvec indexes on import. - pg_search gained WAL-based crash recovery in 0.24.0 (paradedb#4901): without it, any backend crash corrupts BM25 segment metadata and turns a single crash into a recovery loop (paradedb#4935). - PostgreSQL core moved 17.9 -> 17.11; its release notes contain no fix matching this failure signature, ruling the core out. Bump the compose image tags to v0.25.11-pg17 (postgres and langfuse-db-init, prod and dev) and update the docs that pin the old tag. Fresh installs are covered by the existing schema SQL (verified against 0.25.11: extensions, BM25 index and HNSW halfvec indexes all create cleanly). Existing data volumes keep working across the image swap without any action (keyword and vector queries byte-identical in testing); ALTER EXTENSION pg_search/vector UPDATE aligns the SQL catalog afterwards, and migration 000099 is a no-op for 0.25.x by design. The Helm chart pins a different image line and is left alone. Fixes #4077 * fix(migrations): upgrade pg_search catalog to 0.25.11 with the image Swapping in the v0.25.11 image leaves the extension catalog at 0.22.x. Calling extension functions such as paradedb.version_info() against the mismatched catalog segfaults the backend and sends the whole server into crash recovery, so the catalog upgrade is required rather than optional. - Add migration 000115 to update pg_search 0.22.0-0.25.10 to 0.25.11 and pgvector 0.8.0-0.8.3 to 0.8.4 when the server ships those versions. - Skip 000099 on newer images instead of advising UPDATE TO '0.22.6', which leaves the catalog behind the shared library and crashes. - Rewrite the upgrade guide as one 0.22.x -> 0.25.11 path with a required ALTER EXTENSION UPDATE and a note that rollback needs a backup. - Extend scripts/test_paradedb_upgrade.py to verify 0.22.2 -> 0.25.11 by default (--to 0.22.6 keeps the old path) and run CONCURRENTLY migrations outside a transaction like golang-migrate does. --------- Co-authored-by: LuckVd <LuckVd@users.noreply.github.com> Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-10-12 03:50:11 +00:00
image: paradedb/paradedb:v0.25.11-pg17
container_name: WeKnora-postgres-dev
ports:
- "${DB_PORT:-5432}:5432"
environment:
- POSTGRES_USER=${DB_USER}
- POSTGRES_PASSWORD=${DB_PASSWORD}
- POSTGRES_DB=${DB_NAME}
volumes:
- postgres-data-dev:/var/lib/postgresql/data
networks:
- WeKnora-network-dev
healthcheck:
test: ["CMD-SHELL", "pg_isready -U ${DB_USER} -d ${DB_NAME}"]
interval: 10s
timeout: 10s
retries: 3
start_period: 30s
restart: unless-stopped
stop_grace_period: 1m
redis:
image: redis:7.0-alpine
container_name: WeKnora-redis-dev
ports:
- "${REDIS_PORT:-6379}:6379"
volumes:
- redis_data_dev:/data
command: redis-server --appendonly yes --requirepass ${REDIS_PASSWORD}
restart: always
networks:
- WeKnora-network-dev
# See docker-compose.yml searxng-init for rationale (avoid in-place rewrite of
# the repo-tracked settings.yml by the searxng entrypoint).
searxng-init:
image: busybox:1.36
container_name: WeKnora-searxng-init-dev
command: ["sh", "-c", "cp /template/settings.yml /etc/searxng/settings.yml && chmod 0644 /etc/searxng/settings.yml"]
volumes:
- ./docker/searxng/settings.yml:/template/settings.yml:ro
- searxng_config_dev:/etc/searxng
restart: "no"
networks:
- WeKnora-network-dev
profiles:
- searxng
- full
searxng:
image: searxng/searxng:latest
container_name: WeKnora-searxng-dev
# Local dev: bind to loopback by default; the host-side WeKnora process
# reaches it at http://127.0.0.1:${SEARXNG_PORT}.
ports:
- "${SEARXNG_BIND:-127.0.0.1}:${SEARXNG_PORT:-8888}:8080"
volumes:
- searxng_config_dev:/etc/searxng
environment:
- SEARXNG_BASE_URL=http://localhost:${SEARXNG_PORT:-8888}/
- INSTANCE_NAME=weknora-searxng-dev
# See docker-compose.yml for rationale on the default secret.
- SEARXNG_SECRET=${SEARXNG_SECRET:-weknora-default-searxng-secret-rotate-before-exposing-publicly}
cap_drop:
- ALL
cap_add:
- CHOWN
- SETGID
- SETUID
restart: unless-stopped
depends_on:
searxng-init:
condition: service_completed_successfully
networks:
- WeKnora-network-dev
profiles:
- searxng
- full
minio:
image: pgsty/minio:latest
container_name: WeKnora-minio-dev
ports:
- "${MINIO_PORT:-9000}:9000"
- "${MINIO_CONSOLE_PORT:-9001}:9001"
environment:
- MINIO_ROOT_USER=${MINIO_ACCESS_KEY_ID:-minioadmin}
- MINIO_ROOT_PASSWORD=${MINIO_SECRET_ACCESS_KEY:-minioadmin}
command: server --console-address ":9001" /data
volumes:
- minio_data_dev:/data
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
interval: 30s
timeout: 20s
retries: 3
networks:
- WeKnora-network-dev
profiles:
- minio
- full
qdrant:
image: qdrant/qdrant:v1.16.2
container_name: WeKnora-qdrant-dev
ports:
- "${QDRANT_REST_PORT:-6333}:6333"
- "${QDRANT_PORT:-6334}:6334"
volumes:
- qdrant_data_dev:/qdrant/storage
networks:
- WeKnora-network-dev
restart: unless-stopped
profiles:
- qdrant
- full
feat(retriever): activate OpenSearch k-NN driver (PR 3 of 3) Phase 3 (#1440) gate flip. PR 1 (#1445) + PR 2a (#1481) + PR 2b (#1482) laid the type prep + driver skeleton + read/write paths as gated dead code; this PR wires every activation surface so opensearch becomes a registerable VectorStore engine. Activation wiring - internal/types: validEngineTypes / GetVectorStoreTypes (with HNSW bounds + knn_engine enum + Immutable hints) / retrieverEngineMapping / buildEnvStoreForDriver — every gated surface now recognises "opensearch". IndexConfig grows four omitempty HNSW fields (HNSWM / HNSWEFConstruction / HNSWEFSearch / KNNEngine), keeping other engines' serialised config byte-identical. - internal/container: createOpenSearchEngine + the switch case in createEngineServiceFromStore; the RETRIEVE_DRIVER=opensearch env path in initRetrieveEngineRegistry; NewEngineFactory now closes over the AuditLogService (the EngineFactory type itself is unchanged). - internal/application/service/vectorstore_healthcheck.go: a testOpenSearchConnection case so CreateStore's connectivity probe accepts opensearch instead of returning 400. - internal/application/repository/retriever/opensearch/transport.go: NewOpenSearchClient is exported so the factory and env path can build the TLS-hardened client; healthcheck.go reuses the unexported probeVersion / probeKNNPlugin for the service-layer probe. Service-layer validation - validateOpenSearchIndexConfig validates the HNSW caps (m 2-100, ef_construction 2-4096, ef_search 1-10000, knn_engine ∈ lucene|faiss). Shards/replicas continue to be enforced by the flat ValidateIndexConfig. Create-only: UpdateStore mutates the name only. - validateConnectionConfig requires addr for opensearch. Sync implementations (stubs.go shrinks) - CopyIndices (copy.go) mirrors the Elasticsearch / Qdrant pattern — search → BatchSave with the source_id remap for generated questions — so dim/keyword routing and the source_id contract come from BatchSave for free. embeddingMap is keyed by the *target* SourceID because OpenSearch's BatchSave looks up embeddings by SourceID (lookupEmbedding), not by chunk_id (the ES driver's convention). Pagination is from/size; copies larger than max_result_window (default 10000) need the scroll-based async path that lands later. - BatchUpdateChunkEnabledStatus / BatchUpdateChunkTagID (bulk_update.go) group the input by target value and issue one _update_by_query per group over the cross-dim <base>_* pattern. Caller values flow through bound script params only — never string-interpolated into the Painless source — closing the script-injection surface. - inspectByQueryResponse (byquery.go) mirrors inspectBulkResponse: the full failure reason goes to the debug log only; the returned error carries the bounded id + type. - UpdateByQueryParams.Refresh is *bool in opensearch-go v4.6.0 (the same shape as DeleteByQuery's quirk), so refresh=wait_for is not expressible; we use refresh=true. Driver-owned audit (DIP) - A new opensearch.AuditSink interface (with nopSink + WithAuditSink functional option) lets the driver emit opensearch.index_created and opensearch.reindex_executed events without importing any service package — the service layer implements the interface. NewRepository takes opts, so existing 4-arg test call sites keep compiling unchanged. - internal/container/audit_sink.go bridges AuditSink to AuditLogService. When the context carries no tenant (the env-path registration ctx during boot, for example) the adapter skips the emit with a warning rather than silently writing tenant_id=0, which would collide with the system-scope sentinel. Frontend + polish - FieldSchema (frontend/src/api/vector-store.ts) gains min/max/enum/ immutable. VectorStoreSettings.vue is now schema-driven: a closed `enum` renders a t-select; number inputs use the schema's `:min`/`:max` and fall back to the legacy replica-vs-shard heuristic only when the schema does not pin them; a danger-coloured warning fires when insecure_skip_verify is toggled on (the switch and warning are wrapped in a vertical stack so the warning sits on its own row below the switch). - i18n: labels for hnsw_m / hnsw_ef_construction / hnsw_ef_search / knn_engine / insecure_skip_verify plus the warning copy in en-US, ko-KR, zh-CN, ru-RU. - docker-compose.dev.yml: an opensearch profile (single-node 3.3.2 with security plugin disabled for dev only). OpenSearch Dashboards lives in a separate, opt-in opensearch-ui profile so the heavy UI container is not forced up alongside the cluster (the driver e2e is fully curl-verifiable against :9200). The new docs/dev/opensearch-integration-test.md covers the end-to-end exercise and the single-node guidance (set replicas=0 to keep the cluster Green). Gating-guard tests flipped - The "OpenSearch is NOT in validEngineTypes / mapping / types list / env builder / stubs" guard tests from PR 1 / PR 2 are replaced by their positive counterparts in this PR. The test suite was the activation checklist; the activation flip is its diff. Backward compatibility - Additive everywhere. IndexConfig's new HNSW fields are omitempty so other engines' serialised config is byte-identical. Existing Elasticsearch / Qdrant / Milvus / Weaviate / Doris / TencentVectorDB stores are untouched. No migrations. Test plan - go build ./... clean - go vet ./... clean - gofmt -l clean on touched files - go test ./... — only TestOssEnsureBucket_CreateFails (Aliyun OSS endpoint), the docreader gRPC tests, and the doris SQL-shape tests fail; all three are pre-existing on upstream/main and untouched by this PR. - New tests across internal/types, opensearch, service and container — including a full end-to-end env-path test that exercises initRetrieveEngineRegistry with RETRIEVE_DRIVER=opensearch against an httptest cluster.
2026-05-28 09:01:17 +00:00
# OpenSearch k-NN (Phase 3 driver). Single-node dev profile with the
# security plugin disabled → plain HTTP on :9200, no auth/TLS. The image
# bundles the opensearch-knn plugin. For production use a secured,
# multi-node cluster. See website-docs/03-features/05-retrieval-engines.md.
feat(retriever): activate OpenSearch k-NN driver (PR 3 of 3) Phase 3 (#1440) gate flip. PR 1 (#1445) + PR 2a (#1481) + PR 2b (#1482) laid the type prep + driver skeleton + read/write paths as gated dead code; this PR wires every activation surface so opensearch becomes a registerable VectorStore engine. Activation wiring - internal/types: validEngineTypes / GetVectorStoreTypes (with HNSW bounds + knn_engine enum + Immutable hints) / retrieverEngineMapping / buildEnvStoreForDriver — every gated surface now recognises "opensearch". IndexConfig grows four omitempty HNSW fields (HNSWM / HNSWEFConstruction / HNSWEFSearch / KNNEngine), keeping other engines' serialised config byte-identical. - internal/container: createOpenSearchEngine + the switch case in createEngineServiceFromStore; the RETRIEVE_DRIVER=opensearch env path in initRetrieveEngineRegistry; NewEngineFactory now closes over the AuditLogService (the EngineFactory type itself is unchanged). - internal/application/service/vectorstore_healthcheck.go: a testOpenSearchConnection case so CreateStore's connectivity probe accepts opensearch instead of returning 400. - internal/application/repository/retriever/opensearch/transport.go: NewOpenSearchClient is exported so the factory and env path can build the TLS-hardened client; healthcheck.go reuses the unexported probeVersion / probeKNNPlugin for the service-layer probe. Service-layer validation - validateOpenSearchIndexConfig validates the HNSW caps (m 2-100, ef_construction 2-4096, ef_search 1-10000, knn_engine ∈ lucene|faiss). Shards/replicas continue to be enforced by the flat ValidateIndexConfig. Create-only: UpdateStore mutates the name only. - validateConnectionConfig requires addr for opensearch. Sync implementations (stubs.go shrinks) - CopyIndices (copy.go) mirrors the Elasticsearch / Qdrant pattern — search → BatchSave with the source_id remap for generated questions — so dim/keyword routing and the source_id contract come from BatchSave for free. embeddingMap is keyed by the *target* SourceID because OpenSearch's BatchSave looks up embeddings by SourceID (lookupEmbedding), not by chunk_id (the ES driver's convention). Pagination is from/size; copies larger than max_result_window (default 10000) need the scroll-based async path that lands later. - BatchUpdateChunkEnabledStatus / BatchUpdateChunkTagID (bulk_update.go) group the input by target value and issue one _update_by_query per group over the cross-dim <base>_* pattern. Caller values flow through bound script params only — never string-interpolated into the Painless source — closing the script-injection surface. - inspectByQueryResponse (byquery.go) mirrors inspectBulkResponse: the full failure reason goes to the debug log only; the returned error carries the bounded id + type. - UpdateByQueryParams.Refresh is *bool in opensearch-go v4.6.0 (the same shape as DeleteByQuery's quirk), so refresh=wait_for is not expressible; we use refresh=true. Driver-owned audit (DIP) - A new opensearch.AuditSink interface (with nopSink + WithAuditSink functional option) lets the driver emit opensearch.index_created and opensearch.reindex_executed events without importing any service package — the service layer implements the interface. NewRepository takes opts, so existing 4-arg test call sites keep compiling unchanged. - internal/container/audit_sink.go bridges AuditSink to AuditLogService. When the context carries no tenant (the env-path registration ctx during boot, for example) the adapter skips the emit with a warning rather than silently writing tenant_id=0, which would collide with the system-scope sentinel. Frontend + polish - FieldSchema (frontend/src/api/vector-store.ts) gains min/max/enum/ immutable. VectorStoreSettings.vue is now schema-driven: a closed `enum` renders a t-select; number inputs use the schema's `:min`/`:max` and fall back to the legacy replica-vs-shard heuristic only when the schema does not pin them; a danger-coloured warning fires when insecure_skip_verify is toggled on (the switch and warning are wrapped in a vertical stack so the warning sits on its own row below the switch). - i18n: labels for hnsw_m / hnsw_ef_construction / hnsw_ef_search / knn_engine / insecure_skip_verify plus the warning copy in en-US, ko-KR, zh-CN, ru-RU. - docker-compose.dev.yml: an opensearch profile (single-node 3.3.2 with security plugin disabled for dev only). OpenSearch Dashboards lives in a separate, opt-in opensearch-ui profile so the heavy UI container is not forced up alongside the cluster (the driver e2e is fully curl-verifiable against :9200). The new docs/dev/opensearch-integration-test.md covers the end-to-end exercise and the single-node guidance (set replicas=0 to keep the cluster Green). Gating-guard tests flipped - The "OpenSearch is NOT in validEngineTypes / mapping / types list / env builder / stubs" guard tests from PR 1 / PR 2 are replaced by their positive counterparts in this PR. The test suite was the activation checklist; the activation flip is its diff. Backward compatibility - Additive everywhere. IndexConfig's new HNSW fields are omitempty so other engines' serialised config is byte-identical. Existing Elasticsearch / Qdrant / Milvus / Weaviate / Doris / TencentVectorDB stores are untouched. No migrations. Test plan - go build ./... clean - go vet ./... clean - gofmt -l clean on touched files - go test ./... — only TestOssEnsureBucket_CreateFails (Aliyun OSS endpoint), the docreader gRPC tests, and the doris SQL-shape tests fail; all three are pre-existing on upstream/main and untouched by this PR. - New tests across internal/types, opensearch, service and container — including a full end-to-end env-path test that exercises initRetrieveEngineRegistry with RETRIEVE_DRIVER=opensearch against an httptest cluster.
2026-05-28 09:01:17 +00:00
opensearch:
image: opensearchproject/opensearch:3.3.2
container_name: WeKnora-opensearch-dev
environment:
- discovery.type=single-node
# dev only: plain HTTP on :9200, no TLS/auth. The entrypoint script
# honours DISABLE_SECURITY_PLUGIN (env var) to skip both the demo
# install and the OPENSEARCH_INITIAL_ADMIN_PASSWORD requirement.
- DISABLE_SECURITY_PLUGIN=true
- DISABLE_INSTALL_DEMO_CONFIG=true
- OPENSEARCH_JAVA_OPTS=-Xms512m -Xmx512m
- bootstrap.memory_lock=true
ulimits:
memlock:
soft: -1
hard: -1
ports:
- "${OPENSEARCH_PORT:-9200}:9200"
volumes:
- opensearch_data_dev:/usr/share/opensearch/data
networks:
- WeKnora-network-dev
restart: unless-stopped
profiles:
- opensearch
- full
# Also a member of opensearch-ui so the Dashboards depends_on resolves
# when only that profile is active (`--profile opensearch-ui up`).
- opensearch-ui
# Optional UI for visual index/mapping/query inspection. Decoupled from the
# "opensearch" / "full" profiles so the heavy Dashboards container is never
# forced up alongside the cluster — the driver e2e is fully curl-verifiable
# against :9200. Start it on demand with `--profile opensearch-ui up -d`
# (depends_on pulls the cluster in automatically).
opensearch-dashboards:
image: opensearchproject/opensearch-dashboards:3.3.0
container_name: WeKnora-opensearch-dashboards-dev
environment:
- OPENSEARCH_HOSTS=["http://opensearch:9200"]
- DISABLE_SECURITY_DASHBOARDS_PLUGIN=true
ports:
- "${OPENSEARCH_DASHBOARDS_PORT:-5601}:5601"
networks:
- WeKnora-network-dev
depends_on:
- opensearch
restart: unless-stopped
profiles:
- opensearch-ui
milvus:
image: milvusdb/milvus:v2.6.11
container_name: WeKnora-milvus-dev
security_opt:
- seccomp:unconfined
command: ["milvus", "run", "standalone"]
environment:
- ETCD_USE_EMBED=true
- ETCD_DATA_DIR=/var/lib/milvus/etcd
- COMMON_STORAGETYPE=local
- DEPLOY_MODE=STANDALONE
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:9091/healthz"]
interval: 30s
start_period: 90s
timeout: 20s
retries: 3
ports:
- "${MILVUS_PORT:-19530}:19530"
- "${MILVUS_HEALTH_PORT:-9091}:9091"
volumes:
- milvus_data_dev:/var/lib/milvus
networks:
- WeKnora-network-dev
restart: unless-stopped
profiles:
- milvus
- full
neo4j:
image: neo4j:latest
container_name: WeKnora-neo4j-dev
volumes:
- neo4j-data-dev:/data
environment:
- NEO4J_AUTH=${NEO4J_USERNAME:-neo4j}/${NEO4J_PASSWORD:-password}
- NEO4J_apoc_export_file_enabled=true
- NEO4J_apoc_import_file_enabled=true
- NEO4J_apoc_import_file_use__neo4j__config=true
- NEO4JLABS_PLUGINS=["apoc"]
ports:
- "7474:7474"
- "7687:7687"
restart: always
networks:
- WeKnora-network-dev
profiles:
- neo4j
- full
# Sandbox 镜像:仅用于 build/pull,非常驻服务;本地 app 执行 Skills 时按需 docker run 该镜像,用毕即释
sandbox:
image: wechatopenai/weknora-sandbox:${WEKNORA_VERSION:-latest}
container_name: WeKnora-sandbox-dev
build:
context: .
dockerfile: docker/Dockerfile.sandbox
profiles:
- full
command: ["true"]
restart: "no"
docreader:
build:
context: .
dockerfile: docker/Dockerfile.docreader
image: wechatopenai/weknora-docreader:${WEKNORA_VERSION:-latest}
container_name: WeKnora-docreader-dev
ports:
- "${DOCREADER_PORT:-50051}:50051"
volumes:
- docreader-tmp-dev:/tmp/docreader
environment:
feat(compose): align env vars with code + fix helm GraphRAG bug (#2164) * feat(compose): align env vars in docker-compose and .env.example with code docker-compose.yml / docker-compose.dev.yml - app.environment: remove deprecated vars Go app no longer reads (CRYPTO_MASTER_KEY, CRYPTO_SALT, TENANT_AES_KEY, ENABLE_GRAPH_RAG); add missing vars the code actually consumes (OSS/S3/TOS/COS completion, OpenSearch, Tencent VectorDB, Milvus credentials, Redis TLS/namespace, OIDC, audit/invitation/quota, LLM tuning, doc timeouts, etc.) - docreader.environment: complete PDF tuning knobs, SSRF/LOG_LEVEL/gRPC params, GRPC_MTLS_REQUIRE_CLIENT_CERT; fix DOCREADER_PDF_JPEG_QUALITY default 90 -> 85 to match code (config.py) - mcp.environment: add MCP_SERVER_AUTH_TOKEN (required by HTTP transport), WEKNORA_CHAT_TIMEOUT, WEKNORA_VERIFY_SSL, MCP_ALLOWED_UPLOAD_DIRS - dev compose docreader.environment kept symmetric with prod .env.example - reorganize into A-J sections (deploy / data / retrieval / models / parsing / auth / agent / integrations / observability / security) - remove the four deprecated vars, document why - add missing vars, fix NEO4J_URI to bolt:// (matches compose + single-node), fix DORIS_COMPAT_MODE typo, complete docreader PDF tuning defaults Co-Authored-By: Claude <noreply@anthropic.com> * fix(helm): inject NEO4J_ENABLE and drop deprecated TENANT_AES_KEY helm graph bug fix - NEO4J_ENABLE is the sole graph switch the Go app reads (since v0.1.6, ENABLE_GRAPH_RAG is no longer read). helm never injected NEO4J_ENABLE, so GraphRAG was silently broken: setting neo4j.enabled=true gave the app NEO4J_URI/USERNAME/PASSWORD but not the switch, and the UI rejected Node Extractor config with "请正确配置环境变量NEO4J_ENABLE". - app.yaml: inject NEO4J_ENABLE=true inside the neo4j.enabled block; remove the dead ENABLE_GRAPH_RAG injection - NOTES.txt: update GraphRAG instructions (just enable neo4j, no need to set the deprecated ENABLE_GRAPH_RAG) - values.yaml: drop ENABLE_GRAPH_RAG, fix neo4j section comment TENANT_AES_KEY cleanup (deprecated since v0.4.0, encryption now uses SYSTEM_AES_KEY exclusively; Go app no longer reads it) - secrets.yaml: stop generating/looking-up/writing TENANT_AES_KEY, fix stale comment about tenants.api_key rotation - app.yaml: remove TENANT_AES_KEY secretKeyRef - values.yaml: drop tenantAesKey, fix existingSecret key list + comments - cloud-image/firstboot.sh: stop generating/writing/printing TENANT_AES - cloud-image/README.md: drop TENANT_AES_KEY from credential list Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-07-21 07:55:52 +00:00
# ========== 基础 ==========
- TZ=${TZ:-Asia/Shanghai}
feat(compose): align env vars with code + fix helm GraphRAG bug (#2164) * feat(compose): align env vars in docker-compose and .env.example with code docker-compose.yml / docker-compose.dev.yml - app.environment: remove deprecated vars Go app no longer reads (CRYPTO_MASTER_KEY, CRYPTO_SALT, TENANT_AES_KEY, ENABLE_GRAPH_RAG); add missing vars the code actually consumes (OSS/S3/TOS/COS completion, OpenSearch, Tencent VectorDB, Milvus credentials, Redis TLS/namespace, OIDC, audit/invitation/quota, LLM tuning, doc timeouts, etc.) - docreader.environment: complete PDF tuning knobs, SSRF/LOG_LEVEL/gRPC params, GRPC_MTLS_REQUIRE_CLIENT_CERT; fix DOCREADER_PDF_JPEG_QUALITY default 90 -> 85 to match code (config.py) - mcp.environment: add MCP_SERVER_AUTH_TOKEN (required by HTTP transport), WEKNORA_CHAT_TIMEOUT, WEKNORA_VERIFY_SSL, MCP_ALLOWED_UPLOAD_DIRS - dev compose docreader.environment kept symmetric with prod .env.example - reorganize into A-J sections (deploy / data / retrieval / models / parsing / auth / agent / integrations / observability / security) - remove the four deprecated vars, document why - add missing vars, fix NEO4J_URI to bolt:// (matches compose + single-node), fix DORIS_COMPAT_MODE typo, complete docreader PDF tuning defaults Co-Authored-By: Claude <noreply@anthropic.com> * fix(helm): inject NEO4J_ENABLE and drop deprecated TENANT_AES_KEY helm graph bug fix - NEO4J_ENABLE is the sole graph switch the Go app reads (since v0.1.6, ENABLE_GRAPH_RAG is no longer read). helm never injected NEO4J_ENABLE, so GraphRAG was silently broken: setting neo4j.enabled=true gave the app NEO4J_URI/USERNAME/PASSWORD but not the switch, and the UI rejected Node Extractor config with "请正确配置环境变量NEO4J_ENABLE". - app.yaml: inject NEO4J_ENABLE=true inside the neo4j.enabled block; remove the dead ENABLE_GRAPH_RAG injection - NOTES.txt: update GraphRAG instructions (just enable neo4j, no need to set the deprecated ENABLE_GRAPH_RAG) - values.yaml: drop ENABLE_GRAPH_RAG, fix neo4j section comment TENANT_AES_KEY cleanup (deprecated since v0.4.0, encryption now uses SYSTEM_AES_KEY exclusively; Go app no longer reads it) - secrets.yaml: stop generating/looking-up/writing TENANT_AES_KEY, fix stale comment about tenants.api_key rotation - app.yaml: remove TENANT_AES_KEY secretKeyRef - values.yaml: drop tenantAesKey, fix existingSecret key list + comments - cloud-image/firstboot.sh: stop generating/writing/printing TENANT_AES - cloud-image/README.md: drop TENANT_AES_KEY from credential list Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-07-21 07:55:52 +00:00
- LOG_LEVEL=${LOG_LEVEL:-}
- DOCREADER_IMAGE_OUTPUT_DIR=/tmp/docreader
- MAX_FILE_SIZE_MB=${MAX_FILE_SIZE_MB:-}
feat(compose): align env vars with code + fix helm GraphRAG bug (#2164) * feat(compose): align env vars in docker-compose and .env.example with code docker-compose.yml / docker-compose.dev.yml - app.environment: remove deprecated vars Go app no longer reads (CRYPTO_MASTER_KEY, CRYPTO_SALT, TENANT_AES_KEY, ENABLE_GRAPH_RAG); add missing vars the code actually consumes (OSS/S3/TOS/COS completion, OpenSearch, Tencent VectorDB, Milvus credentials, Redis TLS/namespace, OIDC, audit/invitation/quota, LLM tuning, doc timeouts, etc.) - docreader.environment: complete PDF tuning knobs, SSRF/LOG_LEVEL/gRPC params, GRPC_MTLS_REQUIRE_CLIENT_CERT; fix DOCREADER_PDF_JPEG_QUALITY default 90 -> 85 to match code (config.py) - mcp.environment: add MCP_SERVER_AUTH_TOKEN (required by HTTP transport), WEKNORA_CHAT_TIMEOUT, WEKNORA_VERIFY_SSL, MCP_ALLOWED_UPLOAD_DIRS - dev compose docreader.environment kept symmetric with prod .env.example - reorganize into A-J sections (deploy / data / retrieval / models / parsing / auth / agent / integrations / observability / security) - remove the four deprecated vars, document why - add missing vars, fix NEO4J_URI to bolt:// (matches compose + single-node), fix DORIS_COMPAT_MODE typo, complete docreader PDF tuning defaults Co-Authored-By: Claude <noreply@anthropic.com> * fix(helm): inject NEO4J_ENABLE and drop deprecated TENANT_AES_KEY helm graph bug fix - NEO4J_ENABLE is the sole graph switch the Go app reads (since v0.1.6, ENABLE_GRAPH_RAG is no longer read). helm never injected NEO4J_ENABLE, so GraphRAG was silently broken: setting neo4j.enabled=true gave the app NEO4J_URI/USERNAME/PASSWORD but not the switch, and the UI rejected Node Extractor config with "请正确配置环境变量NEO4J_ENABLE". - app.yaml: inject NEO4J_ENABLE=true inside the neo4j.enabled block; remove the dead ENABLE_GRAPH_RAG injection - NOTES.txt: update GraphRAG instructions (just enable neo4j, no need to set the deprecated ENABLE_GRAPH_RAG) - values.yaml: drop ENABLE_GRAPH_RAG, fix neo4j section comment TENANT_AES_KEY cleanup (deprecated since v0.4.0, encryption now uses SYSTEM_AES_KEY exclusively; Go app no longer reads it) - secrets.yaml: stop generating/looking-up/writing TENANT_AES_KEY, fix stale comment about tenants.api_key rotation - app.yaml: remove TENANT_AES_KEY secretKeyRef - values.yaml: drop tenantAesKey, fix existingSecret key list + comments - cloud-image/firstboot.sh: stop generating/writing/printing TENANT_AES - cloud-image/README.md: drop TENANT_AES_KEY from credential list Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-07-21 07:55:52 +00:00
# docreader 对外 HTTP 抓取的 SSRF 白名单(逗号分隔;与 app 共用同名变量)
- SSRF_WHITELIST=${SSRF_WHITELIST:-}
- SSRF_WHITELIST_EXTRA=${SSRF_WHITELIST_EXTRA:-}
feat(security): add a whitelist-only outbound mode that refuses before DNS (#3393) * feat(security): add a whitelist-only outbound mode that refuses before DNS A penetration test of a private deployment found that a host outside SSRF_WHITELIST still produces a DNS query: every outbound guard resolves the name first and judges the addresses afterwards, which is what makes it immune to DNS rebinding, but it also means an attacker-chosen name reaches the resolver and can carry data out of an otherwise offline network (#3378). SSRF_DNS_WHITELIST_ONLY makes the whitelist the whole egress policy, and the check is placed wherever a name is still in hand. Where a URL is available, CheckSSRFWhitelistOnly refuses a host the whitelist does not name, IP literals included: URL validation, the sandbox outbound policy, and the web-fetch target resolver. Where only a dial address is available, CheckDialWhitelistOnly judges hostnames and leaves addresses to the checks that already exist, because an IP arriving at a dialer is either a name something else resolved or a literal the URL layer already refused. That covers the shared SSRF-safe dialer, the web-fetch dialer, the Yunzhijia webhook dialer, and every sandbox transport: the HTTP and websocket data planes, the guarded transport and the Docker engine now share one GuardedDialContext instead of each building its own dialer. Where the client resolves its own target, the name is judged before the client exists. gRPC's resolver runs before any dialer it was given, so the env-configured qdrant and milvus clients are built through small constructors that refuse a non-whitelisted host outright; a whitelisted one is resolved by gRPC as before. docreader enforces the same switch in its own validator, and compose passes the variable to both services. Matching is by name only in this mode: the whitelist's CIDR entries still match an IP literal, but a hostname is no longer resolved to see whether its addresses fall inside one, because that lookup is the query the mode exists to prevent. The value is parsed with ParseBool, and a non-empty value that parses as neither enables the mode: silently leaving an egress lockdown off because an operator wrote "yes" is the one failure mode a security control must not have. Still not covered, and documented as such: the Langfuse OTLP exporter builds its own client and never reaches these guards; and with HTTP(S)_PROXY set the proxy host is dialled unguarded when the dial address equals the proxy URL's host exactly, while a mismatch makes the proxy host itself subject to the whitelist. The switch defaults to off, so nothing changes for deployments that do not set it. * docs(security): document SSRF_DNS_WHITELIST_ONLY in website-docs docs/ has been retired in favour of website-docs/ (#3580), so the notes that lived in docs/QA.md move to the configuration table: the new switch, what to whitelist before turning it on, and the three outbound paths it still does not cover. The existing SSRF_WHITELIST row was also stale: compose gives only the app its SSRF_WHITELIST_EXTRA default (which now includes minio), and docreader's is empty, so "shared by app and docreader" held for SSRF_WHITELIST alone.
2026-09-23 04:02:06 +00:00
- SSRF_DNS_WHITELIST_ONLY=${SSRF_DNS_WHITELIST_ONLY:-}
feat(compose): align env vars with code + fix helm GraphRAG bug (#2164) * feat(compose): align env vars in docker-compose and .env.example with code docker-compose.yml / docker-compose.dev.yml - app.environment: remove deprecated vars Go app no longer reads (CRYPTO_MASTER_KEY, CRYPTO_SALT, TENANT_AES_KEY, ENABLE_GRAPH_RAG); add missing vars the code actually consumes (OSS/S3/TOS/COS completion, OpenSearch, Tencent VectorDB, Milvus credentials, Redis TLS/namespace, OIDC, audit/invitation/quota, LLM tuning, doc timeouts, etc.) - docreader.environment: complete PDF tuning knobs, SSRF/LOG_LEVEL/gRPC params, GRPC_MTLS_REQUIRE_CLIENT_CERT; fix DOCREADER_PDF_JPEG_QUALITY default 90 -> 85 to match code (config.py) - mcp.environment: add MCP_SERVER_AUTH_TOKEN (required by HTTP transport), WEKNORA_CHAT_TIMEOUT, WEKNORA_VERIFY_SSL, MCP_ALLOWED_UPLOAD_DIRS - dev compose docreader.environment kept symmetric with prod .env.example - reorganize into A-J sections (deploy / data / retrieval / models / parsing / auth / agent / integrations / observability / security) - remove the four deprecated vars, document why - add missing vars, fix NEO4J_URI to bolt:// (matches compose + single-node), fix DORIS_COMPAT_MODE typo, complete docreader PDF tuning defaults Co-Authored-By: Claude <noreply@anthropic.com> * fix(helm): inject NEO4J_ENABLE and drop deprecated TENANT_AES_KEY helm graph bug fix - NEO4J_ENABLE is the sole graph switch the Go app reads (since v0.1.6, ENABLE_GRAPH_RAG is no longer read). helm never injected NEO4J_ENABLE, so GraphRAG was silently broken: setting neo4j.enabled=true gave the app NEO4J_URI/USERNAME/PASSWORD but not the switch, and the UI rejected Node Extractor config with "请正确配置环境变量NEO4J_ENABLE". - app.yaml: inject NEO4J_ENABLE=true inside the neo4j.enabled block; remove the dead ENABLE_GRAPH_RAG injection - NOTES.txt: update GraphRAG instructions (just enable neo4j, no need to set the deprecated ENABLE_GRAPH_RAG) - values.yaml: drop ENABLE_GRAPH_RAG, fix neo4j section comment TENANT_AES_KEY cleanup (deprecated since v0.4.0, encryption now uses SYSTEM_AES_KEY exclusively; Go app no longer reads it) - secrets.yaml: stop generating/looking-up/writing TENANT_AES_KEY, fix stale comment about tenants.api_key rotation - app.yaml: remove TENANT_AES_KEY secretKeyRef - values.yaml: drop tenantAesKey, fix existingSecret key list + comments - cloud-image/firstboot.sh: stop generating/writing/printing TENANT_AES - cloud-image/README.md: drop TENANT_AES_KEY from credential list Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-07-21 07:55:52 +00:00
# ========== gRPC 服务端 TLS / 认证 ==========
- GRPC_TLS_ENABLED=${GRPC_TLS_ENABLED:-false}
- GRPC_TLS_CERT=${GRPC_TLS_CERT:-}
- GRPC_TLS_KEY=${GRPC_TLS_KEY:-}
- GRPC_TLS_CA=${GRPC_TLS_CA:-}
- GRPC_TLS_SERVER_NAME=${GRPC_TLS_SERVER_NAME:-}
# true 时强制要求客户端证书(mTLS)
- GRPC_MTLS_REQUIRE_CLIENT_CERT=${GRPC_MTLS_REQUIRE_CLIENT_CERT:-false}
- GRPC_AUTH_TOKEN=${GRPC_AUTH_TOKEN:-}
# ========== gRPC 服务参数 ==========
- DOCREADER_GRPC_MAX_WORKERS=${DOCREADER_GRPC_MAX_WORKERS:-4}
- DOCREADER_GRPC_MAX_FILE_SIZE_MB=${DOCREADER_GRPC_MAX_FILE_SIZE_MB:-${MAX_FILE_SIZE_MB:-50}}
- DOCREADER_GRPC_PORT=${DOCREADER_GRPC_PORT:-50051}
# ========== 解析通用 ==========
- DOCREADER_DOCX_MAX_PAGES=${DOCREADER_DOCX_MAX_PAGES:-0}
- DOCREADER_MARKITDOWN_MAX_WORKERS=${DOCREADER_MARKITDOWN_MAX_WORKERS:-1}
# 出站 HTTP/HTTPS 代理(抓取网页 / 远程图片时)
- DOCREADER_EXTERNAL_HTTP_PROXY=${DOCREADER_EXTERNAL_HTTP_PROXY:-}
- DOCREADER_EXTERNAL_HTTPS_PROXY=${DOCREADER_EXTERNAL_HTTPS_PROXY:-}
# ========== OpenDataLoader hybrid ==========
- DOCREADER_ODL_MAX_WORKERS=${DOCREADER_ODL_MAX_WORKERS:-1}
- DOCREADER_ODL_HYBRID=${DOCREADER_ODL_HYBRID:-off}
- DOCREADER_ODL_HYBRID_URL=${DOCREADER_ODL_HYBRID_URL:-http://odl-hybrid:5002}
- DOCREADER_ODL_HYBRID_MODE=${DOCREADER_ODL_HYBRID_MODE:-auto}
- DOCREADER_ODL_HYBRID_FALLBACK=${DOCREADER_ODL_HYBRID_FALLBACK:-false}
- DOCREADER_ODL_MARKDOWN_WITH_HTML=${DOCREADER_ODL_MARKDOWN_WITH_HTML:-false}
feat(compose): align env vars with code + fix helm GraphRAG bug (#2164) * feat(compose): align env vars in docker-compose and .env.example with code docker-compose.yml / docker-compose.dev.yml - app.environment: remove deprecated vars Go app no longer reads (CRYPTO_MASTER_KEY, CRYPTO_SALT, TENANT_AES_KEY, ENABLE_GRAPH_RAG); add missing vars the code actually consumes (OSS/S3/TOS/COS completion, OpenSearch, Tencent VectorDB, Milvus credentials, Redis TLS/namespace, OIDC, audit/invitation/quota, LLM tuning, doc timeouts, etc.) - docreader.environment: complete PDF tuning knobs, SSRF/LOG_LEVEL/gRPC params, GRPC_MTLS_REQUIRE_CLIENT_CERT; fix DOCREADER_PDF_JPEG_QUALITY default 90 -> 85 to match code (config.py) - mcp.environment: add MCP_SERVER_AUTH_TOKEN (required by HTTP transport), WEKNORA_CHAT_TIMEOUT, WEKNORA_VERIFY_SSL, MCP_ALLOWED_UPLOAD_DIRS - dev compose docreader.environment kept symmetric with prod .env.example - reorganize into A-J sections (deploy / data / retrieval / models / parsing / auth / agent / integrations / observability / security) - remove the four deprecated vars, document why - add missing vars, fix NEO4J_URI to bolt:// (matches compose + single-node), fix DORIS_COMPAT_MODE typo, complete docreader PDF tuning defaults Co-Authored-By: Claude <noreply@anthropic.com> * fix(helm): inject NEO4J_ENABLE and drop deprecated TENANT_AES_KEY helm graph bug fix - NEO4J_ENABLE is the sole graph switch the Go app reads (since v0.1.6, ENABLE_GRAPH_RAG is no longer read). helm never injected NEO4J_ENABLE, so GraphRAG was silently broken: setting neo4j.enabled=true gave the app NEO4J_URI/USERNAME/PASSWORD but not the switch, and the UI rejected Node Extractor config with "请正确配置环境变量NEO4J_ENABLE". - app.yaml: inject NEO4J_ENABLE=true inside the neo4j.enabled block; remove the dead ENABLE_GRAPH_RAG injection - NOTES.txt: update GraphRAG instructions (just enable neo4j, no need to set the deprecated ENABLE_GRAPH_RAG) - values.yaml: drop ENABLE_GRAPH_RAG, fix neo4j section comment TENANT_AES_KEY cleanup (deprecated since v0.4.0, encryption now uses SYSTEM_AES_KEY exclusively; Go app no longer reads it) - secrets.yaml: stop generating/looking-up/writing TENANT_AES_KEY, fix stale comment about tenants.api_key rotation - app.yaml: remove TENANT_AES_KEY secretKeyRef - values.yaml: drop tenantAesKey, fix existingSecret key list + comments - cloud-image/firstboot.sh: stop generating/writing/printing TENANT_AES - cloud-image/README.md: drop TENANT_AES_KEY from credential list Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-07-21 07:55:52 +00:00
# ========== PDF 渲染 ==========
- DOCREADER_PDF_RENDER_MAX_WORKERS=${DOCREADER_PDF_RENDER_MAX_WORKERS:-1}
# 单个 PDF 内部扫描页渲染并行进程数(pdfium 非线程安全)。留空走代码默认 min(4,cpu),
# 避免在低核容器上过度并行(写死数值会覆盖 CPU 感知逻辑)。
- DOCREADER_PDF_RENDER_PARALLELISM=${DOCREADER_PDF_RENDER_PARALLELISM:-}
- DOCREADER_PDF_RENDER_DPI=${DOCREADER_PDF_RENDER_DPI:-200}
feat(compose): align env vars with code + fix helm GraphRAG bug (#2164) * feat(compose): align env vars in docker-compose and .env.example with code docker-compose.yml / docker-compose.dev.yml - app.environment: remove deprecated vars Go app no longer reads (CRYPTO_MASTER_KEY, CRYPTO_SALT, TENANT_AES_KEY, ENABLE_GRAPH_RAG); add missing vars the code actually consumes (OSS/S3/TOS/COS completion, OpenSearch, Tencent VectorDB, Milvus credentials, Redis TLS/namespace, OIDC, audit/invitation/quota, LLM tuning, doc timeouts, etc.) - docreader.environment: complete PDF tuning knobs, SSRF/LOG_LEVEL/gRPC params, GRPC_MTLS_REQUIRE_CLIENT_CERT; fix DOCREADER_PDF_JPEG_QUALITY default 90 -> 85 to match code (config.py) - mcp.environment: add MCP_SERVER_AUTH_TOKEN (required by HTTP transport), WEKNORA_CHAT_TIMEOUT, WEKNORA_VERIFY_SSL, MCP_ALLOWED_UPLOAD_DIRS - dev compose docreader.environment kept symmetric with prod .env.example - reorganize into A-J sections (deploy / data / retrieval / models / parsing / auth / agent / integrations / observability / security) - remove the four deprecated vars, document why - add missing vars, fix NEO4J_URI to bolt:// (matches compose + single-node), fix DORIS_COMPAT_MODE typo, complete docreader PDF tuning defaults Co-Authored-By: Claude <noreply@anthropic.com> * fix(helm): inject NEO4J_ENABLE and drop deprecated TENANT_AES_KEY helm graph bug fix - NEO4J_ENABLE is the sole graph switch the Go app reads (since v0.1.6, ENABLE_GRAPH_RAG is no longer read). helm never injected NEO4J_ENABLE, so GraphRAG was silently broken: setting neo4j.enabled=true gave the app NEO4J_URI/USERNAME/PASSWORD but not the switch, and the UI rejected Node Extractor config with "请正确配置环境变量NEO4J_ENABLE". - app.yaml: inject NEO4J_ENABLE=true inside the neo4j.enabled block; remove the dead ENABLE_GRAPH_RAG injection - NOTES.txt: update GraphRAG instructions (just enable neo4j, no need to set the deprecated ENABLE_GRAPH_RAG) - values.yaml: drop ENABLE_GRAPH_RAG, fix neo4j section comment TENANT_AES_KEY cleanup (deprecated since v0.4.0, encryption now uses SYSTEM_AES_KEY exclusively; Go app no longer reads it) - secrets.yaml: stop generating/looking-up/writing TENANT_AES_KEY, fix stale comment about tenants.api_key rotation - app.yaml: remove TENANT_AES_KEY secretKeyRef - values.yaml: drop tenantAesKey, fix existingSecret key list + comments - cloud-image/firstboot.sh: stop generating/writing/printing TENANT_AES - cloud-image/README.md: drop TENANT_AES_KEY from credential list Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>
2026-07-21 07:55:52 +00:00
# JPEG 质量(代码默认 85;compose 此前误写 90,已对齐)
- DOCREADER_PDF_JPEG_QUALITY=${DOCREADER_PDF_JPEG_QUALITY:-85}
# 渲染页图最大长边像素(防超大页撑爆 gRPC 消息上限;密集中文建议 >=1600)
- DOCREADER_PDF_RENDER_MAX_EDGE=${DOCREADER_PDF_RENDER_MAX_EDGE:-2000}
# 强制 PDF 全页按扫描件解析(文本层差但可 OCR 时;速度/成本上升)
- DOCREADER_PDF_FORCE_SCANNED=${DOCREADER_PDF_FORCE_SCANNED:-false}
# ========== PDF 版式 / 文本调优 ==========
# glyph 间距超过 median 字宽的多少倍时插空格(默认 0.4)
- DOCREADER_PDF_WORD_GAP_WIDTH_RATIO=${DOCREADER_PDF_WORD_GAP_WIDTH_RATIO:-0.4}
# 丢弃窄边栏(arXiv 侧栏)的页宽比例阈值(默认 0.12)
- DOCREADER_PDF_MARGIN_COL_WIDTH_RATIO=${DOCREADER_PDF_MARGIN_COL_WIDTH_RATIO:-0.12}
- DOCREADER_PDF_MIN_HEADING_LINE_CHARS=${DOCREADER_PDF_MIN_HEADING_LINE_CHARS:-8}
# 清理 U+FFFE/软连字符、剥离矢量图轴文字、图表区按 JPEG 渲染
- DOCREADER_PDF_SANITIZE_TEXT=${DOCREADER_PDF_SANITIZE_TEXT:-true}
- DOCREADER_PDF_STRIP_CHART_DEBRIS=${DOCREADER_PDF_STRIP_CHART_DEBRIS:-true}
- DOCREADER_PDF_RENDER_VECTOR_FIGURES=${DOCREADER_PDF_RENDER_VECTOR_FIGURES:-true}
- DOCREADER_PDF_DETECT_HEADINGS=${DOCREADER_PDF_DETECT_HEADINGS:-}
- DOCREADER_PDF_LAYOUT_ORDERING=${DOCREADER_PDF_LAYOUT_ORDERING:-}
- DOCREADER_PDF_FILTER_HIDDEN_TEXT=${DOCREADER_PDF_FILTER_HIDDEN_TEXT:-}
# 扫描件判定:图片面积占比 >= 此值视为扫描页(默认留空走代码默认)
- DOCREADER_PDF_SCAN_IMAGE_RATIO=${DOCREADER_PDF_SCAN_IMAGE_RATIO:-}
- DOCREADER_PDF_SCAN_MIN_CHARS=${DOCREADER_PDF_SCAN_MIN_CHARS:-}
# 嵌入图片抽取
- DOCREADER_PDF_EXTRACT_EMBEDDED_IMAGES=${DOCREADER_PDF_EXTRACT_EMBEDDED_IMAGES:-}
- DOCREADER_PDF_EMBED_MIN_PIXELS=${DOCREADER_PDF_EMBED_MIN_PIXELS:-}
- DOCREADER_PDF_EMBED_MIN_AREA_RATIO=${DOCREADER_PDF_EMBED_MIN_AREA_RATIO:-}
- DOCREADER_PDF_EMBED_REPEAT_PAGE_FRAC=${DOCREADER_PDF_EMBED_REPEAT_PAGE_FRAC:-}
- DOCREADER_PDF_EMBED_MAX_IMAGES=${DOCREADER_PDF_EMBED_MAX_IMAGES:-}
# 图表区识别
- DOCREADER_PDF_MIN_CHART_REGION_AREA=${DOCREADER_PDF_MIN_CHART_REGION_AREA:-}
- DOCREADER_PDF_MIN_CHART_REGION_CHARS=${DOCREADER_PDF_MIN_CHART_REGION_CHARS:-}
- DOCREADER_PDF_MAX_CHART_REGION_AREA=${DOCREADER_PDF_MAX_CHART_REGION_AREA:-}
- DOCREADER_PDF_MAX_FIGURE_HEIGHT_RATIO=${DOCREADER_PDF_MAX_FIGURE_HEIGHT_RATIO:-}
healthcheck:
test: ["CMD", "grpc_health_probe", "-addr=localhost:50051"]
interval: 30s
timeout: 10s
retries: 3
start_period: 60s
networks:
- WeKnora-network-dev
restart: unless-stopped
extra_hosts:
- "host.docker.internal:host-gateway"
# OpenDataLoader hybrid backend (optional). Enable profile "odl-hybrid" and set
# DOCREADER_ODL_HYBRID=docling-fast on docreader. Default --no-ocr (no EasyOCR).
# Local build only — not published to Docker Hub.
odl-hybrid:
build:
context: .
dockerfile: docker/Dockerfile.odl-hybrid
image: weknora-odl-hybrid:local
container_name: WeKnora-odl-hybrid
profiles:
- odl-hybrid
ports:
- "${ODL_HYBRID_PORT:-5002}:5002"
environment:
# Default --no-ocr (digital PDFs). Scanned PDFs: use builtin OCR / MinerU, or
# ODL_HYBRID_EXTRA_ARGS="--force-ocr" (needs EasyOCR + libGL in image).
- ODL_HYBRID_EXTRA_ARGS=${ODL_HYBRID_EXTRA_ARGS:---no-ocr}
networks:
- WeKnora-network-dev
restart: unless-stopped
2026-03-30 03:13:44 +00:00
dex:
image: dexidp/dex:latest
container_name: WeKnora-dex-dev
ports:
- "5556:5556"
volumes:
- ./misc/dex-config.yaml:/etc/dex/config.yaml
command: ["dex", "serve", "/etc/dex/config.yaml"]
profiles:
- dex
- full
feat(observability): integrate Langfuse for LLM token tracking and tracing Closes #620 #497. Add opt-in Langfuse observability covering all five model types (chat, embedding, rerank, VLM, ASR) with HTTP-request-scoped traces and Docker Compose support (both cloud and self-hosted). Core package internal/tracing/langfuse: - HTTP client with batched async ingestion (non-blocking in request path) - Sampling, environment / release tagging, and graceful fallback when LANGFUSE_* env vars are absent (wrappers become no-ops) - Gin middleware opens one trace per traced request and finishes it after the handler chain returns, attaching method / path / user / session - Trace context is stored under a typed key exported from internal/types so logger.CloneContext can preserve it across handler / goroutine boundaries (otherwise each LLM call auto-created an orphan trace, fragmenting one request into many) Per-model generation wrappers (opt-in via NewChat/NewEmbedder/...): - chat: captures prompt, streaming output, token usage + TTFT - embedding: approximates tokens when the provider omits usage - rerank: previews query/docs, summarizes results to keep payload small - vlm: records image count and total bytes, never uploads raw pixels - asr: records file size and audio duration, never uploads audio bytes Async title generation (GenerateTitleAsync) now forwards the trace key into the goroutine so title calls appear under the parent chat trace. Docker Compose: - LANGFUSE_* env passthrough on the `app` service for cloud deployments - Optional `langfuse` profile spins up a self-hosted Langfuse stack that reuses WeKnora's existing PostgreSQL (separate database via an idempotent init container that fixes ICU collation drift) and Redis (separate DB number), adding only ClickHouse, MinIO, web and worker containers - web/worker entrypoints URL-encode DB_PASSWORD / REDIS_PASSWORD at start to avoid Prisma P1013 when passwords contain @ / # / etc. Docs: docs/Langfuse集成.md covers cloud vs self-hosted, per-model usage strategy, code map, and resource footprint.
2026-04-23 17:57:12 +00:00
# ---------------------------------------------------------------------------
# Langfuse 自建栈(dev 对称版)
#
# 用法:
# docker compose -f docker-compose.dev.yml --profile langfuse up -d
#
# 本地 app (go run) 需要的环境变量:
# export LANGFUSE_HOST=http://localhost:3000
# export LANGFUSE_PUBLIC_KEY=pk-lf-xxx
# export LANGFUSE_SECRET_KEY=sk-lf-xxx
#
# 复用 dev 已有的 postgres(独立 langfuse 数据库)和 redis(DB 1),
# 新增:clickhouse、minio、web、worker + 一次性 db-init,和生产版结构一致。
# ---------------------------------------------------------------------------
# 复用 dev 已有的 ParadeDB 镜像,不额外拉 postgres 镜像
langfuse-db-init:
fix(deploy): bump paradedb image to v0.25.11-pg17 (#4120) * fix(deploy): bump paradedb image to v0.25.11-pg17 Batch-importing large knowledge bases on the pinned paradedb/paradedb:v0.22.6-pg17 image drives PostgreSQL into a PANIC/crash-recovery loop (corrupted page pointers in shared buffers, amcheck clean, no OOM), taking every ingest task down with it. Three independent fixes upstream cover this exact write path, and the pinned image predates all of them: - pgvector 0.8.2 fixed a buffer overflow in parallel HNSW index builds, 0.8.3 fixed possible index corruption during HNSW vacuuming, and 0.8.4 fixed inserts during HNSW vacuuming; the image ships pgvector 0.8.1, and the embeddings table maintains three HNSW halfvec indexes on import. - pg_search gained WAL-based crash recovery in 0.24.0 (paradedb#4901): without it, any backend crash corrupts BM25 segment metadata and turns a single crash into a recovery loop (paradedb#4935). - PostgreSQL core moved 17.9 -> 17.11; its release notes contain no fix matching this failure signature, ruling the core out. Bump the compose image tags to v0.25.11-pg17 (postgres and langfuse-db-init, prod and dev) and update the docs that pin the old tag. Fresh installs are covered by the existing schema SQL (verified against 0.25.11: extensions, BM25 index and HNSW halfvec indexes all create cleanly). Existing data volumes keep working across the image swap without any action (keyword and vector queries byte-identical in testing); ALTER EXTENSION pg_search/vector UPDATE aligns the SQL catalog afterwards, and migration 000099 is a no-op for 0.25.x by design. The Helm chart pins a different image line and is left alone. Fixes #4077 * fix(migrations): upgrade pg_search catalog to 0.25.11 with the image Swapping in the v0.25.11 image leaves the extension catalog at 0.22.x. Calling extension functions such as paradedb.version_info() against the mismatched catalog segfaults the backend and sends the whole server into crash recovery, so the catalog upgrade is required rather than optional. - Add migration 000115 to update pg_search 0.22.0-0.25.10 to 0.25.11 and pgvector 0.8.0-0.8.3 to 0.8.4 when the server ships those versions. - Skip 000099 on newer images instead of advising UPDATE TO '0.22.6', which leaves the catalog behind the shared library and crashes. - Rewrite the upgrade guide as one 0.22.x -> 0.25.11 path with a required ALTER EXTENSION UPDATE and a note that rollback needs a backup. - Extend scripts/test_paradedb_upgrade.py to verify 0.22.2 -> 0.25.11 by default (--to 0.22.6 keeps the old path) and run CONCURRENTLY migrations outside a transaction like golang-migrate does. --------- Co-authored-by: LuckVd <LuckVd@users.noreply.github.com> Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-10-12 03:50:11 +00:00
image: paradedb/paradedb:v0.25.11-pg17
feat(observability): integrate Langfuse for LLM token tracking and tracing Closes #620 #497. Add opt-in Langfuse observability covering all five model types (chat, embedding, rerank, VLM, ASR) with HTTP-request-scoped traces and Docker Compose support (both cloud and self-hosted). Core package internal/tracing/langfuse: - HTTP client with batched async ingestion (non-blocking in request path) - Sampling, environment / release tagging, and graceful fallback when LANGFUSE_* env vars are absent (wrappers become no-ops) - Gin middleware opens one trace per traced request and finishes it after the handler chain returns, attaching method / path / user / session - Trace context is stored under a typed key exported from internal/types so logger.CloneContext can preserve it across handler / goroutine boundaries (otherwise each LLM call auto-created an orphan trace, fragmenting one request into many) Per-model generation wrappers (opt-in via NewChat/NewEmbedder/...): - chat: captures prompt, streaming output, token usage + TTFT - embedding: approximates tokens when the provider omits usage - rerank: previews query/docs, summarizes results to keep payload small - vlm: records image count and total bytes, never uploads raw pixels - asr: records file size and audio duration, never uploads audio bytes Async title generation (GenerateTitleAsync) now forwards the trace key into the goroutine so title calls appear under the parent chat trace. Docker Compose: - LANGFUSE_* env passthrough on the `app` service for cloud deployments - Optional `langfuse` profile spins up a self-hosted Langfuse stack that reuses WeKnora's existing PostgreSQL (separate database via an idempotent init container that fixes ICU collation drift) and Redis (separate DB number), adding only ClickHouse, MinIO, web and worker containers - web/worker entrypoints URL-encode DB_PASSWORD / REDIS_PASSWORD at start to avoid Prisma P1013 when passwords contain @ / # / etc. Docs: docs/Langfuse集成.md covers cloud vs self-hosted, per-model usage strategy, code map, and resource footprint.
2026-04-23 17:57:12 +00:00
container_name: WeKnora-langfuse-db-init-dev
depends_on:
postgres:
condition: service_healthy
environment:
PGPASSWORD: ${DB_PASSWORD}
# ${LANGFUSE_DB_NAME:-langfuse} / ${DB_USER} 由 compose 解析成字面量后再传给 shell。
entrypoint: ["sh", "-c"]
command:
- |
set -e
echo "[langfuse-db-init] ensuring database '${LANGFUSE_DB_NAME:-langfuse}' exists..."
# 先刷新现有库的 collation(镜像 ICU 2.36 与宿主 2.41 不匹配时必须做),否则 CREATE DATABASE 会失败
psql -h postgres -U ${DB_USER} -d postgres -v ON_ERROR_STOP=0 -c "ALTER DATABASE template1 REFRESH COLLATION VERSION;" >/dev/null 2>&1 || true
psql -h postgres -U ${DB_USER} -d postgres -v ON_ERROR_STOP=0 -c "ALTER DATABASE postgres REFRESH COLLATION VERSION;" >/dev/null 2>&1 || true
# 幂等创建:已存在则跳过;不存在则从 template0 克隆(template0 永远不会有 collation 漂移)
if psql -h postgres -U ${DB_USER} -d postgres -tAc "SELECT 1 FROM pg_database WHERE datname='${LANGFUSE_DB_NAME:-langfuse}'" | grep -q 1; then
echo "[langfuse-db-init] database '${LANGFUSE_DB_NAME:-langfuse}' already exists, skipping."
else
psql -h postgres -U ${DB_USER} -d postgres -v ON_ERROR_STOP=1 -c "CREATE DATABASE \"${LANGFUSE_DB_NAME:-langfuse}\" TEMPLATE template0;"
echo "[langfuse-db-init] database '${LANGFUSE_DB_NAME:-langfuse}' created."
fi
echo "[langfuse-db-init] done."
networks:
- WeKnora-network-dev
restart: "no"
profiles:
- langfuse
- full
langfuse-clickhouse:
image: clickhouse/clickhouse-server:24.8
container_name: WeKnora-langfuse-clickhouse-dev
restart: unless-stopped
user: "101:101"
environment:
CLICKHOUSE_DB: default
CLICKHOUSE_USER: ${LANGFUSE_CLICKHOUSE_USER:-clickhouse}
CLICKHOUSE_PASSWORD: ${LANGFUSE_CLICKHOUSE_PASSWORD:-clickhouse}
volumes:
- langfuse_clickhouse_data_dev:/var/lib/clickhouse
- langfuse_clickhouse_logs_dev:/var/log/clickhouse-server
healthcheck:
test: wget --no-verbose --tries=1 --spider http://localhost:8123/ping || exit 1
interval: 5s
timeout: 5s
retries: 10
start_period: 10s
networks:
- WeKnora-network-dev
profiles:
- langfuse
- full
langfuse-minio:
image: pgsty/minio:RELEASE.2026-08-04T00-00-00Z
feat(observability): integrate Langfuse for LLM token tracking and tracing Closes #620 #497. Add opt-in Langfuse observability covering all five model types (chat, embedding, rerank, VLM, ASR) with HTTP-request-scoped traces and Docker Compose support (both cloud and self-hosted). Core package internal/tracing/langfuse: - HTTP client with batched async ingestion (non-blocking in request path) - Sampling, environment / release tagging, and graceful fallback when LANGFUSE_* env vars are absent (wrappers become no-ops) - Gin middleware opens one trace per traced request and finishes it after the handler chain returns, attaching method / path / user / session - Trace context is stored under a typed key exported from internal/types so logger.CloneContext can preserve it across handler / goroutine boundaries (otherwise each LLM call auto-created an orphan trace, fragmenting one request into many) Per-model generation wrappers (opt-in via NewChat/NewEmbedder/...): - chat: captures prompt, streaming output, token usage + TTFT - embedding: approximates tokens when the provider omits usage - rerank: previews query/docs, summarizes results to keep payload small - vlm: records image count and total bytes, never uploads raw pixels - asr: records file size and audio duration, never uploads audio bytes Async title generation (GenerateTitleAsync) now forwards the trace key into the goroutine so title calls appear under the parent chat trace. Docker Compose: - LANGFUSE_* env passthrough on the `app` service for cloud deployments - Optional `langfuse` profile spins up a self-hosted Langfuse stack that reuses WeKnora's existing PostgreSQL (separate database via an idempotent init container that fixes ICU collation drift) and Redis (separate DB number), adding only ClickHouse, MinIO, web and worker containers - web/worker entrypoints URL-encode DB_PASSWORD / REDIS_PASSWORD at start to avoid Prisma P1013 when passwords contain @ / # / etc. Docs: docs/Langfuse集成.md covers cloud vs self-hosted, per-model usage strategy, code map, and resource footprint.
2026-04-23 17:57:12 +00:00
container_name: WeKnora-langfuse-minio-dev
restart: unless-stopped
entrypoint: sh
command: -c 'mkdir -p /data/langfuse && minio server --address ":9000" --console-address ":9001" /data'
environment:
MINIO_ROOT_USER: ${LANGFUSE_MINIO_USER:-langfuseminio}
MINIO_ROOT_PASSWORD: ${LANGFUSE_MINIO_PASSWORD:-langfuseminiosecret}
ports:
- "${LANGFUSE_MINIO_S3_PORT:-9100}:9000"
- "${LANGFUSE_MINIO_CONSOLE_PORT:-9101}:9001"
volumes:
- langfuse_minio_data_dev:/data
healthcheck:
test: ["CMD", "mc", "ready", "local"]
interval: 5s
timeout: 10s
retries: 5
networks:
- WeKnora-network-dev
profiles:
- langfuse
- full
langfuse-worker:
image: langfuse/langfuse-worker:3
container_name: WeKnora-langfuse-worker-dev
restart: unless-stopped
depends_on: &langfuse-dev-depends-on
langfuse-db-init:
condition: service_completed_successfully
redis:
condition: service_started
langfuse-clickhouse:
condition: service_healthy
langfuse-minio:
condition: service_healthy
# wrapper entrypoint 把 DB_PASSWORD / REDIS_PASSWORD URL 编码后再拼 URL,
# 避免密码含 '@' / '#' 等字符导致 Prisma P1013 解析失败。
# 注意:compose 覆盖 entrypoint 会清空镜像默认 CMD,所以末尾写死原始命令。
entrypoint:
- /bin/sh
- -ec
- |
_enc() { node -e 'process.stdout.write(encodeURIComponent(process.argv[1]))' "$$1"; }
DU=$$(_enc "$$_LF_DB_USER")
DP=$$(_enc "$$_LF_DB_PASSWORD")
RP=$$(_enc "$$_LF_REDIS_PASSWORD")
export DATABASE_URL="postgresql://$$DU:$$DP@postgres:5432/$$_LF_DB_NAME"
export REDIS_CONNECTION_STRING="redis://:$$RP@redis:6379/$$_LF_REDIS_DB"
unset _LF_DB_USER _LF_DB_PASSWORD _LF_REDIS_PASSWORD
exec dumb-init -- ./worker/entrypoint.sh node worker/dist/index.js
environment: &langfuse-dev-env
# 原始凭证(未 URL 编码),由 entrypoint wrapper 读取并组装
_LF_DB_USER: ${DB_USER}
_LF_DB_PASSWORD: ${DB_PASSWORD}
_LF_DB_NAME: ${LANGFUSE_DB_NAME:-langfuse}
_LF_REDIS_PASSWORD: ${REDIS_PASSWORD}
_LF_REDIS_DB: ${LANGFUSE_REDIS_DB:-1}
SALT: ${LANGFUSE_SALT:-weknora-langfuse-dev-salt-change-me}
ENCRYPTION_KEY: ${LANGFUSE_ENCRYPTION_KEY:-0000000000000000000000000000000000000000000000000000000000000000}
NEXTAUTH_URL: ${LANGFUSE_NEXTAUTH_URL:-http://localhost:3000}
NEXTAUTH_SECRET: ${LANGFUSE_NEXTAUTH_SECRET:-weknora-langfuse-dev-nextauth-secret-change-me}
TELEMETRY_ENABLED: ${LANGFUSE_TELEMETRY_ENABLED:-false}
LANGFUSE_ENABLE_EXPERIMENTAL_FEATURES: "false"
CLICKHOUSE_URL: http://langfuse-clickhouse:8123
CLICKHOUSE_MIGRATION_URL: clickhouse://langfuse-clickhouse:9000
CLICKHOUSE_USER: ${LANGFUSE_CLICKHOUSE_USER:-clickhouse}
CLICKHOUSE_PASSWORD: ${LANGFUSE_CLICKHOUSE_PASSWORD:-clickhouse}
CLICKHOUSE_CLUSTER_ENABLED: "false"
LANGFUSE_S3_EVENT_UPLOAD_BUCKET: langfuse
LANGFUSE_S3_EVENT_UPLOAD_REGION: auto
LANGFUSE_S3_EVENT_UPLOAD_ACCESS_KEY_ID: ${LANGFUSE_MINIO_USER:-langfuseminio}
LANGFUSE_S3_EVENT_UPLOAD_SECRET_ACCESS_KEY: ${LANGFUSE_MINIO_PASSWORD:-langfuseminiosecret}
LANGFUSE_S3_EVENT_UPLOAD_ENDPOINT: http://langfuse-minio:9000
LANGFUSE_S3_EVENT_UPLOAD_FORCE_PATH_STYLE: "true"
LANGFUSE_S3_EVENT_UPLOAD_PREFIX: events/
LANGFUSE_S3_MEDIA_UPLOAD_BUCKET: langfuse
LANGFUSE_S3_MEDIA_UPLOAD_REGION: auto
LANGFUSE_S3_MEDIA_UPLOAD_ACCESS_KEY_ID: ${LANGFUSE_MINIO_USER:-langfuseminio}
LANGFUSE_S3_MEDIA_UPLOAD_SECRET_ACCESS_KEY: ${LANGFUSE_MINIO_PASSWORD:-langfuseminiosecret}
LANGFUSE_S3_MEDIA_UPLOAD_ENDPOINT: ${LANGFUSE_S3_MEDIA_UPLOAD_ENDPOINT:-http://localhost:9100}
LANGFUSE_S3_MEDIA_UPLOAD_FORCE_PATH_STYLE: "true"
LANGFUSE_S3_MEDIA_UPLOAD_PREFIX: media/
networks:
- WeKnora-network-dev
profiles:
- langfuse
- full
langfuse-web:
image: langfuse/langfuse:3
container_name: WeKnora-langfuse-web-dev
restart: unless-stopped
depends_on: *langfuse-dev-depends-on
ports:
- "${LANGFUSE_WEB_PORT:-3000}:3000"
entrypoint:
- /bin/sh
- -ec
- |
_enc() { node -e 'process.stdout.write(encodeURIComponent(process.argv[1]))' "$$1"; }
DU=$$(_enc "$$_LF_DB_USER")
DP=$$(_enc "$$_LF_DB_PASSWORD")
RP=$$(_enc "$$_LF_REDIS_PASSWORD")
export DATABASE_URL="postgresql://$$DU:$$DP@postgres:5432/$$_LF_DB_NAME"
export REDIS_CONNECTION_STRING="redis://:$$RP@redis:6379/$$_LF_REDIS_DB"
unset _LF_DB_USER _LF_DB_PASSWORD _LF_REDIS_PASSWORD
if [ -n "$$NEXT_PUBLIC_LANGFUSE_CLOUD_REGION" ]; then
exec dumb-init -- ./web/entrypoint.sh node --import dd-trace/initialize.mjs ./web/server.js --keepAliveTimeout 110000
else
exec dumb-init -- ./web/entrypoint.sh node ./web/server.js --keepAliveTimeout 110000
fi
environment:
<<: *langfuse-dev-env
LANGFUSE_INIT_ORG_ID: ${LANGFUSE_INIT_ORG_ID:-}
LANGFUSE_INIT_ORG_NAME: ${LANGFUSE_INIT_ORG_NAME:-}
LANGFUSE_INIT_PROJECT_ID: ${LANGFUSE_INIT_PROJECT_ID:-}
LANGFUSE_INIT_PROJECT_NAME: ${LANGFUSE_INIT_PROJECT_NAME:-}
LANGFUSE_INIT_PROJECT_PUBLIC_KEY: ${LANGFUSE_INIT_PROJECT_PUBLIC_KEY:-}
LANGFUSE_INIT_PROJECT_SECRET_KEY: ${LANGFUSE_INIT_PROJECT_SECRET_KEY:-}
LANGFUSE_INIT_USER_EMAIL: ${LANGFUSE_INIT_USER_EMAIL:-}
LANGFUSE_INIT_USER_NAME: ${LANGFUSE_INIT_USER_NAME:-}
LANGFUSE_INIT_USER_PASSWORD: ${LANGFUSE_INIT_USER_PASSWORD:-}
networks:
- WeKnora-network-dev
profiles:
- langfuse
- full
2026-03-30 03:13:44 +00:00
networks:
WeKnora-network-dev:
driver: bridge
volumes:
postgres-data-dev:
redis_data_dev:
minio_data_dev:
neo4j-data-dev:
qdrant_data_dev:
feat(retriever): activate OpenSearch k-NN driver (PR 3 of 3) Phase 3 (#1440) gate flip. PR 1 (#1445) + PR 2a (#1481) + PR 2b (#1482) laid the type prep + driver skeleton + read/write paths as gated dead code; this PR wires every activation surface so opensearch becomes a registerable VectorStore engine. Activation wiring - internal/types: validEngineTypes / GetVectorStoreTypes (with HNSW bounds + knn_engine enum + Immutable hints) / retrieverEngineMapping / buildEnvStoreForDriver — every gated surface now recognises "opensearch". IndexConfig grows four omitempty HNSW fields (HNSWM / HNSWEFConstruction / HNSWEFSearch / KNNEngine), keeping other engines' serialised config byte-identical. - internal/container: createOpenSearchEngine + the switch case in createEngineServiceFromStore; the RETRIEVE_DRIVER=opensearch env path in initRetrieveEngineRegistry; NewEngineFactory now closes over the AuditLogService (the EngineFactory type itself is unchanged). - internal/application/service/vectorstore_healthcheck.go: a testOpenSearchConnection case so CreateStore's connectivity probe accepts opensearch instead of returning 400. - internal/application/repository/retriever/opensearch/transport.go: NewOpenSearchClient is exported so the factory and env path can build the TLS-hardened client; healthcheck.go reuses the unexported probeVersion / probeKNNPlugin for the service-layer probe. Service-layer validation - validateOpenSearchIndexConfig validates the HNSW caps (m 2-100, ef_construction 2-4096, ef_search 1-10000, knn_engine ∈ lucene|faiss). Shards/replicas continue to be enforced by the flat ValidateIndexConfig. Create-only: UpdateStore mutates the name only. - validateConnectionConfig requires addr for opensearch. Sync implementations (stubs.go shrinks) - CopyIndices (copy.go) mirrors the Elasticsearch / Qdrant pattern — search → BatchSave with the source_id remap for generated questions — so dim/keyword routing and the source_id contract come from BatchSave for free. embeddingMap is keyed by the *target* SourceID because OpenSearch's BatchSave looks up embeddings by SourceID (lookupEmbedding), not by chunk_id (the ES driver's convention). Pagination is from/size; copies larger than max_result_window (default 10000) need the scroll-based async path that lands later. - BatchUpdateChunkEnabledStatus / BatchUpdateChunkTagID (bulk_update.go) group the input by target value and issue one _update_by_query per group over the cross-dim <base>_* pattern. Caller values flow through bound script params only — never string-interpolated into the Painless source — closing the script-injection surface. - inspectByQueryResponse (byquery.go) mirrors inspectBulkResponse: the full failure reason goes to the debug log only; the returned error carries the bounded id + type. - UpdateByQueryParams.Refresh is *bool in opensearch-go v4.6.0 (the same shape as DeleteByQuery's quirk), so refresh=wait_for is not expressible; we use refresh=true. Driver-owned audit (DIP) - A new opensearch.AuditSink interface (with nopSink + WithAuditSink functional option) lets the driver emit opensearch.index_created and opensearch.reindex_executed events without importing any service package — the service layer implements the interface. NewRepository takes opts, so existing 4-arg test call sites keep compiling unchanged. - internal/container/audit_sink.go bridges AuditSink to AuditLogService. When the context carries no tenant (the env-path registration ctx during boot, for example) the adapter skips the emit with a warning rather than silently writing tenant_id=0, which would collide with the system-scope sentinel. Frontend + polish - FieldSchema (frontend/src/api/vector-store.ts) gains min/max/enum/ immutable. VectorStoreSettings.vue is now schema-driven: a closed `enum` renders a t-select; number inputs use the schema's `:min`/`:max` and fall back to the legacy replica-vs-shard heuristic only when the schema does not pin them; a danger-coloured warning fires when insecure_skip_verify is toggled on (the switch and warning are wrapped in a vertical stack so the warning sits on its own row below the switch). - i18n: labels for hnsw_m / hnsw_ef_construction / hnsw_ef_search / knn_engine / insecure_skip_verify plus the warning copy in en-US, ko-KR, zh-CN, ru-RU. - docker-compose.dev.yml: an opensearch profile (single-node 3.3.2 with security plugin disabled for dev only). OpenSearch Dashboards lives in a separate, opt-in opensearch-ui profile so the heavy UI container is not forced up alongside the cluster (the driver e2e is fully curl-verifiable against :9200). The new docs/dev/opensearch-integration-test.md covers the end-to-end exercise and the single-node guidance (set replicas=0 to keep the cluster Green). Gating-guard tests flipped - The "OpenSearch is NOT in validEngineTypes / mapping / types list / env builder / stubs" guard tests from PR 1 / PR 2 are replaced by their positive counterparts in this PR. The test suite was the activation checklist; the activation flip is its diff. Backward compatibility - Additive everywhere. IndexConfig's new HNSW fields are omitempty so other engines' serialised config is byte-identical. Existing Elasticsearch / Qdrant / Milvus / Weaviate / Doris / TencentVectorDB stores are untouched. No migrations. Test plan - go build ./... clean - go vet ./... clean - gofmt -l clean on touched files - go test ./... — only TestOssEnsureBucket_CreateFails (Aliyun OSS endpoint), the docreader gRPC tests, and the doris SQL-shape tests fail; all three are pre-existing on upstream/main and untouched by this PR. - New tests across internal/types, opensearch, service and container — including a full end-to-end env-path test that exercises initRetrieveEngineRegistry with RETRIEVE_DRIVER=opensearch against an httptest cluster.
2026-05-28 09:01:17 +00:00
opensearch_data_dev:
milvus_data_dev:
docreader-tmp-dev:
feat(observability): integrate Langfuse for LLM token tracking and tracing Closes #620 #497. Add opt-in Langfuse observability covering all five model types (chat, embedding, rerank, VLM, ASR) with HTTP-request-scoped traces and Docker Compose support (both cloud and self-hosted). Core package internal/tracing/langfuse: - HTTP client with batched async ingestion (non-blocking in request path) - Sampling, environment / release tagging, and graceful fallback when LANGFUSE_* env vars are absent (wrappers become no-ops) - Gin middleware opens one trace per traced request and finishes it after the handler chain returns, attaching method / path / user / session - Trace context is stored under a typed key exported from internal/types so logger.CloneContext can preserve it across handler / goroutine boundaries (otherwise each LLM call auto-created an orphan trace, fragmenting one request into many) Per-model generation wrappers (opt-in via NewChat/NewEmbedder/...): - chat: captures prompt, streaming output, token usage + TTFT - embedding: approximates tokens when the provider omits usage - rerank: previews query/docs, summarizes results to keep payload small - vlm: records image count and total bytes, never uploads raw pixels - asr: records file size and audio duration, never uploads audio bytes Async title generation (GenerateTitleAsync) now forwards the trace key into the goroutine so title calls appear under the parent chat trace. Docker Compose: - LANGFUSE_* env passthrough on the `app` service for cloud deployments - Optional `langfuse` profile spins up a self-hosted Langfuse stack that reuses WeKnora's existing PostgreSQL (separate database via an idempotent init container that fixes ICU collation drift) and Redis (separate DB number), adding only ClickHouse, MinIO, web and worker containers - web/worker entrypoints URL-encode DB_PASSWORD / REDIS_PASSWORD at start to avoid Prisma P1013 when passwords contain @ / # / etc. Docs: docs/Langfuse集成.md covers cloud vs self-hosted, per-model usage strategy, code map, and resource footprint.
2026-04-23 17:57:12 +00:00
langfuse_clickhouse_data_dev:
langfuse_clickhouse_logs_dev:
langfuse_minio_data_dev:
searxng_config_dev: