Component
core/ai-agent/dify
The Dify API and console server — the control plane of a self-hosted Dify installation. It serves the console API the browser front end calls, the published application API, and the file endpoints, and it owns the platform's relational model: workspaces, applications, workflow definitions, datasets and the encrypted model-provider credentials. It stores that model in a PostgreSQL backend wired through the `backend` uses-socket, keeps sessions and the Celery task queue in a Redis-compatible cache wired through `cache`, and reads and writes dataset embeddings in a vector datastore wired through `vector_store`. Three sibling services complete the platform and reach it through their own sockets: code nodes execute in the sandbox wired through `sandbox`, model and tool plugins run in the plugin runtime wired through `plugin_daemon`, and outbound requests to addresses a user supplied are routed through the forward proxy wired through `ssrf_proxy`, so a workflow cannot reach a private address directly. Holds no durable state of its own — the backend, the cache and the vector datastore are the systems of record — so it renders as a stateless server. Exports its host, port and protocol to consumers via the uses topology. An application written in Dify's own export format, set as app_definition, is imported into the installation at deploy under the owner account the operator names.
版本
来源
- 内容摘要
- sha256:9934ad23e2257de50668185805cec5cca8464cbd259c8c1be033b87b904d84d2
- 发布时间
- 2026-11-10T10:07:57Z
- 签名身份
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
签名
- 官方application/vnd.dev.sigstore.bundle.v0.3+json
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
sha256:3b4123cad4b6844c96e70344448c245ffa5af8d97df01b59545c1919ac0684f2
此版本的引用
oci://hub.aggrega.ai/component/core/ai-agent/dify:1.0.0开发者参数
开发者在 Aggregate 中设置的值。
扩展 BaseComponents#/schemas/BaseAgentParameter
| 名称 | 类型 | 默认值 | 必需 | 描述 |
|---|---|---|---|---|
| vector_index_prefix | string | Vector_index | 否 | Name prefix the platform gives the collections it creates in the wired vector datastore. Two installations sharing one datastore keep their collections apart by carrying different prefixes. |
| top_k_max | integer (min 1) | 10 | 否 | Highest retrieval top-k an application in this installation may request. |
| max_parallel_limit | integer (min 1) | 10 | 否 | Highest parallel-branch count a workflow in this installation may run. |
| max_iterations | integer (min 1) | 99 | 否 | Highest iteration count an iteration node in this installation may run. |
| max_tools | integer (min 1) | 10 | 否 | Highest number of tools an agent in this installation may be given. |
| indexing_max_segmentation_tokens | integer (min 1) | 4000 | 否 | Longest segment, in tokens, the dataset indexer produces when it splits a document. |
| app_definition | string | — | 否 | An application in Dify's own DSL, the YAML Dify exports for an application, carried verbatim. Realized by the helm target: when set, a one-shot step imports it once the installation is deployed. The step performs Dify's first-time setup if it has not run, creating the owner account named by infra.owner_email with the password attached to the owner_password slot; signs in as that account; leaves an application already present under the definition's app.name as it is; and otherwise imports the definition through Dify's console import, confirming the import when Dify holds it for confirmation, as it does for a DSL version newer than the installation's. When set, infra.owner_email and the owner_password slot are required and the build halts without them. When unset, nothing is imported and no step is rendered. An Aggregate's text is evaluated as a template before it is read, so a definition carrying Dify's own {{#...#}} variable references halts the build when written into an Aggregate as it stands; supply it as a parameter the Release fills, written into this value through toJson, and it arrives as written. |
运维规格
运维人员按环境调整的基础设施规格。
| 名称 | 类型 | 默认值 | 必需 | 描述 |
|---|---|---|---|---|
| port | integer (min 1024, max 65535) | 5001 | 否 | Console-API and application-API listen port consumers connect to. |
| engine_version | string | 1.17.0 | 否 | Dify API container image tag. The worker, the scheduler and this server run the same image, so a Release moves all three together. |
| log_level | string (DEBUG | INFO | WARNING | ERROR | CRITICAL) | INFO | 否 | Log verbosity the server emits. |
| external_base_url | string | 否 | Externally reachable base URL of the installation, as a browser and an API client see it — the address the ingress tier publishes. The server composes the console, application, service-API and file URLs from it, which is what makes shared links and emailed links resolve. Left empty, the server derives each URL from the incoming request, which suits an installation reached only in-cluster. | |
| owner_email | string | — | 否 | Email address of the installation's owner account, read only when values.app_definition is set. The step that imports the application creates this account when it performs Dify's first-time setup, and signs in as it; on an installation whose setup has already run, it names an existing account allowed to import applications, and the password attached to the owner_password slot is that account's. Required when values.app_definition is set: the build halts when it is empty. It has no default. |
| compute | object | — | 否 | — |
| overrides | object (open) | — | 否 | Provider-specific overrides. Accepts any nested structure. Each Recipe documents which keys it reads. |
输出契约
此组件通过 uses 拓扑向使用方发布的值。
| 名称 | 类型 | 默认值 | 必需 | 描述 |
|---|---|---|---|---|
| host | string | — | 是 | In-cluster DNS name of the Service fronting the console and application APIs. The front end and the workers dial this name for every piece of data they show or act on. |
| port | integer | — | 是 | TCP port that Service accepts API requests on. It follows the port an operator set in the Release, so a consumer reads it rather than assuming a default. |
| protocol | string | — | 否 | URL scheme to reach `host` and `port` over, which a consumer composes its base URL on. |
uses 套接字
此组件用于建立连接的依赖套接字。通过某个套接字接入的每个连接,其目标都必须满足该套接字的标签选择器,且每个连接都可以在该套接字声明的槽位中携带附加项。必需槽位须由 Aggregate 或 Release 通过该套接字接入的每个连接来填充。
backend
- 选择器
- component.aggrega.ai/category=datastore
- 注入
- env
经由此套接字的每个连接可填充的槽位
| 槽位 | 选择器 | 必需 | 注入 | 敏感 | 描述 |
|---|---|---|---|---|---|
| credential | feature.aggrega.ai/kind=secret | 否 | env | 是 | Optional password the server presents to the backend this connection reaches, shared with that backend. When attached, supplies the backend password via the credential subsystem; unattached, the Recipe uses the development literal `apppass`, which this catalog publishes, so every Release that leaves the slot unattached shares that password. |
cache
- 选择器
- component.aggrega.ai/category=datastore
- 注入
- env
经由此套接字的每个连接可填充的槽位
| 槽位 | 选择器 | 必需 | 注入 | 敏感 | 描述 |
|---|---|---|---|---|---|
| server_ca | feature.aggrega.ai/kind=secret | 否 | file | 是 | Optional authority the server checks the cache's certificate against while the cache publishes protocol valkey-tls or redis-tls, where the image does not already trust the authority that signs it. Its Secret holds ca.crt. The Recipe mounts the whole Secret read-only and points the cache client and the task broker at the file. The build halts on a server_ca publishing no Secret name, and on one wired to a cache served without TLS. Fill it with core/referenced-secret. |
vector_store
- 选择器
- datastore.aggrega.ai/engine in (vector, semantic-memory, search)
- 注入
- env
此套接字未声明附加槽位,因此经由它的连接不携带任何附加项。
sandbox
- 选择器
- component.aggrega.ai/category=ai-agent
- 注入
- env
经由此套接字的每个连接可填充的槽位
| 槽位 | 选择器 | 必需 | 注入 | 敏感 | 描述 |
|---|---|---|---|---|---|
| credential | feature.aggrega.ai/kind=secret | 否 | env | 是 | Optional execution-key credential the server presents on every request to the sandbox this connection reaches. The same credential is attached to the code_execution_key slot on the sandbox, so both ends hold the same value. Unattached, the Recipe uses the pinned development literal `dify-sandbox`, suitable for evaluation only and published in this catalog, so every Release that leaves the slot unattached shares it. |
plugin_daemon
- 选择器
- component.aggrega.ai/category=ai-agent
- 注入
- env
经由此套接字的每个连接可填充的槽位
| 槽位 | 选择器 | 必需 | 注入 | 敏感 | 描述 |
|---|---|---|---|---|---|
| credential | feature.aggrega.ai/kind=secret | 否 | env | 是 | Optional credential the server presents on every call it makes to the plugin runtime this connection reaches. The runtime holds the same key in its plugin_daemon_key slot and the task worker presents it on its own connection, so the credential is attached to all three or to none: attaching it to some of them leaves the rest carrying a different value, which renders cleanly and is refused when the call is made. Unattached, the Recipe uses the pinned development literal `dify-plugin-daemon-server-key`, suitable for evaluation only and published in this catalog, so every Release that leaves the slot unattached shares it. |
ssrf_proxy
- 选择器
- component.aggrega.ai/category=ai-agent
- 注入
- env
此套接字未声明附加槽位,因此经由它的连接不携带任何附加项。
附加槽位
Feature 附加到此组件时所用的命名绑定点。槽位的选择器限定哪个 Feature 可以填充该槽位,其 inject 列表则指明 Feature 的内容可以如何交付。必需槽位必须在每个实例上完成绑定,可以通过实例上的附加,也可以通过其上层作用域的附加;敏感槽位则声明为用于处理机密内容。Feature 也可以以任何槽位都未声明的名称进行附加。
| 槽位 | 选择器 | 必需 | 注入 | 敏感 | 描述 |
|---|---|---|---|---|---|
| secret_key | feature.aggrega.ai/kind=secret | 是 | env | 是 | Required application-secret credential. The server signs session cookies with it and encrypts stored model-provider credentials under it, and the task worker decrypts them with the same secret. There is no default: the build halts when nothing fills this slot. |
| inner_api_key | feature.aggrega.ai/kind=secret | 否 | env | 是 | Optional credential the plugin runtime presents on every call back into the server's internal API, which the server compares against its own. The server and the task worker declare this slot under the same name and the plugin runtime presents it on its connection to the server, so the credential is attached to all three or to none: attaching it to some of them leaves the rest carrying a different value, which renders cleanly and is refused when the call is made. Unattached, the Recipe uses the pinned development literal `dify-plugin-inner-api-key`, suitable for evaluation only and published in this catalog, so every Release that leaves the slot unattached shares it. |
| owner_password | feature.aggrega.ai/kind=secret | 否 | env | 是 | Password of the owner account named by infra.owner_email, read only when values.app_definition is set: the step that imports the application at deploy sets it when it performs Dify's first-time setup, and signs in with it. Required then, and the build halts when nothing fills this slot; there is no development default. The step receives it by reference, as a Kubernetes secretKeyRef to the Secret the credential publishes, so the password appears in no file the Recipe renders, and a credential publishing no Secret name and data key halts the build. Dify accepts a password of at least eight characters holding both letters and digits. |
自注入允许列表
env
关系
与其他已发布实体之间的类型化边。没有已发布目标的引用会呈现为断开的边,而不是链接。
使用
- 使用使用套接字 «backend»
component.aggrega.ai/category=datastore
附加槽位:credential
core/datastore/chroma v1.0.0 →core/datastore/cognee v1.0.0 →core/datastore/documentdb v1.0.0 →core/datastore/elasticsearch v1.0.0 →core/datastore/etcd v1.0.0 →core/datastore/ferretdb v1.0.0 →core/datastore/mariadb v1.0.0 →core/datastore/mariadb-operator v1.0.0 →core/datastore/memcached v1.0.0 →core/datastore/milvus v1.0.0 →core/datastore/mysql v1.0.0 →core/datastore/mysql-innodb-cluster v1.0.0 →core/datastore/mysql-operator v1.0.0 →core/datastore/opensearch v1.0.0 →core/datastore/pgvector v1.0.0 →core/datastore/postgres v1.0.0 →core/datastore/qdrant v1.0.0 →core/datastore/redis v1.0.0 →core/datastore/timescaledb v1.0.0 →core/datastore/valkey v1.0.0 →core/datastore/weaviate v1.0.0 → - 使用使用套接字 «cache»
component.aggrega.ai/category=datastore
附加槽位:server_ca
core/datastore/chroma v1.0.0 →core/datastore/cognee v1.0.0 →core/datastore/documentdb v1.0.0 →core/datastore/elasticsearch v1.0.0 →core/datastore/etcd v1.0.0 →core/datastore/ferretdb v1.0.0 →core/datastore/mariadb v1.0.0 →core/datastore/mariadb-operator v1.0.0 →core/datastore/memcached v1.0.0 →core/datastore/milvus v1.0.0 →core/datastore/mysql v1.0.0 →core/datastore/mysql-innodb-cluster v1.0.0 →core/datastore/mysql-operator v1.0.0 →core/datastore/opensearch v1.0.0 →core/datastore/pgvector v1.0.0 →core/datastore/postgres v1.0.0 →core/datastore/qdrant v1.0.0 →core/datastore/redis v1.0.0 →core/datastore/timescaledb v1.0.0 →core/datastore/valkey v1.0.0 →core/datastore/weaviate v1.0.0 → - 使用使用套接字 «vector_store»
datastore.aggrega.ai/engine in (vector, semantic-memory, search)
未声明附加槽位。
- 使用使用套接字 «sandbox»
component.aggrega.ai/category=ai-agent
附加槽位:credential
core/ai-agent/a2a-remote v1.0.0 →core/ai-agent/agent-framework v1.0.0 →core/ai-agent/agent-framework v1.1.0 →core/ai-agent/agenta-api v1.0.0 →core/ai-agent/agenta-cron v1.0.0 →core/ai-agent/agenta-migrations v1.0.0 →core/ai-agent/agenta-runner v1.0.0 →core/ai-agent/agenta-services v1.0.0 →core/ai-agent/agenta-web v1.0.0 →core/ai-agent/agenta-web-mobile v1.0.0 →core/ai-agent/agenta-worker-queues v1.0.0 →core/ai-agent/agenta-worker-streams v1.0.0 →core/ai-agent/anthropic v1.0.0 →core/ai-agent/autogen v1.0.0 →core/ai-agent/autogpt v1.0.0 →core/ai-agent/bedrock v1.0.0 →core/ai-agent/bland v1.0.0 →core/ai-agent/claude-agent-sdk v1.0.0 →core/ai-agent/crewai v1.0.0 →core/ai-agent/crewai v1.1.0 →core/ai-agent/dify v1.1.0 →core/ai-agent/dify-plugin-daemon v1.0.0 →core/ai-agent/dify-sandbox v1.0.0 →core/ai-agent/dify-ssrf-proxy v1.0.0 →core/ai-agent/dify-web v1.0.0 →core/ai-agent/dify-web v1.1.0 →core/ai-agent/dify-worker v1.0.0 →core/ai-agent/dify-worker v1.1.0 →core/ai-agent/dify-worker-beat v1.0.0 →core/ai-agent/dify-worker-beat v1.1.0 →core/ai-agent/dynamiq v1.0.0 →core/ai-agent/flowise v1.0.0 →core/ai-agent/flowise v1.1.0 →core/ai-agent/gemini v1.0.0 →core/ai-agent/google-adk v1.0.0 →core/ai-agent/google-adk v1.1.0 →core/ai-agent/griptape v1.0.0 →core/ai-agent/gumloop v1.0.0 →core/ai-agent/haystack v1.0.0 →core/ai-agent/langflow v1.0.0 →core/ai-agent/langflow v1.1.0 →core/ai-agent/langgraph v1.0.0 →core/ai-agent/langgraph v1.1.0 →core/ai-agent/letta v1.0.0 →core/ai-agent/librechat v1.0.0 →core/ai-agent/librechat v1.1.0 →core/ai-agent/librechat v1.2.0 →core/ai-agent/lindy v1.0.0 →core/ai-agent/livekit-agent-worker v1.0.0 →core/ai-agent/llamaindex v1.0.0 →core/ai-agent/mastra v1.0.0 →core/ai-agent/metagpt v1.0.0 →core/ai-agent/n8n v1.0.0 →core/ai-agent/n8n v1.1.0 →core/ai-agent/open-webui v1.0.0 →core/ai-agent/openai-agents-sdk v1.0.0 →core/ai-agent/openclaw v1.0.0 →core/ai-agent/openhands v1.0.0 →core/ai-agent/phidata v1.0.0 →core/ai-agent/promptflow v1.0.0 →core/ai-agent/pydantic-ai v1.0.0 →core/ai-agent/retell v1.0.0 →core/ai-agent/rivet v1.0.0 →core/ai-agent/semantic-kernel v1.0.0 →core/ai-agent/smolagents v1.0.0 →core/ai-agent/vapi v1.0.0 →core/ai-agent/vertex-ai v1.0.0 → - 使用使用套接字 «plugin_daemon»
component.aggrega.ai/category=ai-agent
附加槽位:credential
core/ai-agent/a2a-remote v1.0.0 →core/ai-agent/agent-framework v1.0.0 →core/ai-agent/agent-framework v1.1.0 →core/ai-agent/agenta-api v1.0.0 →core/ai-agent/agenta-cron v1.0.0 →core/ai-agent/agenta-migrations v1.0.0 →core/ai-agent/agenta-runner v1.0.0 →core/ai-agent/agenta-services v1.0.0 →core/ai-agent/agenta-web v1.0.0 →core/ai-agent/agenta-web-mobile v1.0.0 →core/ai-agent/agenta-worker-queues v1.0.0 →core/ai-agent/agenta-worker-streams v1.0.0 →core/ai-agent/anthropic v1.0.0 →core/ai-agent/autogen v1.0.0 →core/ai-agent/autogpt v1.0.0 →core/ai-agent/bedrock v1.0.0 →core/ai-agent/bland v1.0.0 →core/ai-agent/claude-agent-sdk v1.0.0 →core/ai-agent/crewai v1.0.0 →core/ai-agent/crewai v1.1.0 →core/ai-agent/dify v1.1.0 →core/ai-agent/dify-plugin-daemon v1.0.0 →core/ai-agent/dify-sandbox v1.0.0 →core/ai-agent/dify-ssrf-proxy v1.0.0 →core/ai-agent/dify-web v1.0.0 →core/ai-agent/dify-web v1.1.0 →core/ai-agent/dify-worker v1.0.0 →core/ai-agent/dify-worker v1.1.0 →core/ai-agent/dify-worker-beat v1.0.0 →core/ai-agent/dify-worker-beat v1.1.0 →core/ai-agent/dynamiq v1.0.0 →core/ai-agent/flowise v1.0.0 →core/ai-agent/flowise v1.1.0 →core/ai-agent/gemini v1.0.0 →core/ai-agent/google-adk v1.0.0 →core/ai-agent/google-adk v1.1.0 →core/ai-agent/griptape v1.0.0 →core/ai-agent/gumloop v1.0.0 →core/ai-agent/haystack v1.0.0 →core/ai-agent/langflow v1.0.0 →core/ai-agent/langflow v1.1.0 →core/ai-agent/langgraph v1.0.0 →core/ai-agent/langgraph v1.1.0 →core/ai-agent/letta v1.0.0 →core/ai-agent/librechat v1.0.0 →core/ai-agent/librechat v1.1.0 →core/ai-agent/librechat v1.2.0 →core/ai-agent/lindy v1.0.0 →core/ai-agent/livekit-agent-worker v1.0.0 →core/ai-agent/llamaindex v1.0.0 →core/ai-agent/mastra v1.0.0 →core/ai-agent/metagpt v1.0.0 →core/ai-agent/n8n v1.0.0 →core/ai-agent/n8n v1.1.0 →core/ai-agent/open-webui v1.0.0 →core/ai-agent/openai-agents-sdk v1.0.0 →core/ai-agent/openclaw v1.0.0 →core/ai-agent/openhands v1.0.0 →core/ai-agent/phidata v1.0.0 →core/ai-agent/promptflow v1.0.0 →core/ai-agent/pydantic-ai v1.0.0 →core/ai-agent/retell v1.0.0 →core/ai-agent/rivet v1.0.0 →core/ai-agent/semantic-kernel v1.0.0 →core/ai-agent/smolagents v1.0.0 →core/ai-agent/vapi v1.0.0 →core/ai-agent/vertex-ai v1.0.0 → - 使用使用套接字 «ssrf_proxy»
component.aggrega.ai/category=ai-agent
未声明附加槽位。
core/ai-agent/a2a-remote v1.0.0 →core/ai-agent/agent-framework v1.0.0 →core/ai-agent/agent-framework v1.1.0 →core/ai-agent/agenta-api v1.0.0 →core/ai-agent/agenta-cron v1.0.0 →core/ai-agent/agenta-migrations v1.0.0 →core/ai-agent/agenta-runner v1.0.0 →core/ai-agent/agenta-services v1.0.0 →core/ai-agent/agenta-web v1.0.0 →core/ai-agent/agenta-web-mobile v1.0.0 →core/ai-agent/agenta-worker-queues v1.0.0 →core/ai-agent/agenta-worker-streams v1.0.0 →core/ai-agent/anthropic v1.0.0 →core/ai-agent/autogen v1.0.0 →core/ai-agent/autogpt v1.0.0 →core/ai-agent/bedrock v1.0.0 →core/ai-agent/bland v1.0.0 →core/ai-agent/claude-agent-sdk v1.0.0 →core/ai-agent/crewai v1.0.0 →core/ai-agent/crewai v1.1.0 →core/ai-agent/dify v1.1.0 →core/ai-agent/dify-plugin-daemon v1.0.0 →core/ai-agent/dify-sandbox v1.0.0 →core/ai-agent/dify-ssrf-proxy v1.0.0 →core/ai-agent/dify-web v1.0.0 →core/ai-agent/dify-web v1.1.0 →core/ai-agent/dify-worker v1.0.0 →core/ai-agent/dify-worker v1.1.0 →core/ai-agent/dify-worker-beat v1.0.0 →core/ai-agent/dify-worker-beat v1.1.0 →core/ai-agent/dynamiq v1.0.0 →core/ai-agent/flowise v1.0.0 →core/ai-agent/flowise v1.1.0 →core/ai-agent/gemini v1.0.0 →core/ai-agent/google-adk v1.0.0 →core/ai-agent/google-adk v1.1.0 →core/ai-agent/griptape v1.0.0 →core/ai-agent/gumloop v1.0.0 →core/ai-agent/haystack v1.0.0 →core/ai-agent/langflow v1.0.0 →core/ai-agent/langflow v1.1.0 →core/ai-agent/langgraph v1.0.0 →core/ai-agent/langgraph v1.1.0 →core/ai-agent/letta v1.0.0 →core/ai-agent/librechat v1.0.0 →core/ai-agent/librechat v1.1.0 →core/ai-agent/librechat v1.2.0 →core/ai-agent/lindy v1.0.0 →core/ai-agent/livekit-agent-worker v1.0.0 →core/ai-agent/llamaindex v1.0.0 →core/ai-agent/mastra v1.0.0 →core/ai-agent/metagpt v1.0.0 →core/ai-agent/n8n v1.0.0 →core/ai-agent/n8n v1.1.0 →core/ai-agent/open-webui v1.0.0 →core/ai-agent/openai-agents-sdk v1.0.0 →core/ai-agent/openclaw v1.0.0 →core/ai-agent/openhands v1.0.0 →core/ai-agent/phidata v1.0.0 →core/ai-agent/promptflow v1.0.0 →core/ai-agent/pydantic-ai v1.0.0 →core/ai-agent/retell v1.0.0 →core/ai-agent/rivet v1.0.0 →core/ai-agent/semantic-kernel v1.0.0 →core/ai-agent/smolagents v1.0.0 →core/ai-agent/vapi v1.0.0 →core/ai-agent/vertex-ai v1.0.0 → - $ref扩展模式(values)
BaseComponents#/schemas/BaseAgentParameter
被使用
使用套接字 «runner»
使用套接字 «api»
使用套接字 «runner»
使用套接字 «api»
使用套接字 «services»
使用套接字 «api»
使用套接字 «services»
使用套接字 «services»
使用套接字 «sandbox»
使用套接字 «plugin_daemon»
使用套接字 «ssrf_proxy»
使用套接字 «api»
使用套接字 «ssrf_proxy»
使用套接字 «api»
使用套接字 «api»
使用套接字 «sandbox»
使用套接字 «plugin_daemon»
使用套接字 «ssrf_proxy»
使用套接字 «sandbox»
使用套接字 «plugin_daemon»
使用套接字 «ssrf_proxy»
使用套接字 «target_agent»
使用套接字 «upstream»
使用套接字 «forward_target»
使用套接字 «scrape_target»
使用套接字 «store»
适用于
适用于
适用于
适用于
适用于
适用于
适用于
实现