neo4j-aura-agent-skill
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseWhen to Use
适用场景
- Creating or configuring an Aura Agent on an existing AuraDB instance
- Adding/updating tools (CypherTemplate, SimilaritySearch, Text2Cypher) to an agent
- Deploying an agent for external access (REST API endpoint or MCP server)
- Invoking an agent with natural language queries via REST API
- Listing, reading, or deleting existing agents in a project
- 在现有AuraDB实例上创建或配置Aura Agent
- 为代理添加/更新工具(CypherTemplate、SimilaritySearch、Text2Cypher)
- 部署代理以供外部访问(REST API端点或MCP服务器)
- 通过REST API使用自然语言查询调用代理
- 列出、查看或删除项目中已有的代理
When NOT to Use
不适用场景
- Creating/managing AuraDB instances →
neo4j-aura-provisioning-skill - Creating vector indexes →
neo4j-vector-index-skill - Running Cypher directly →
neo4j-cypher-skill - Building Aura Graph Analytics sessions →
neo4j-aura-graph-analytics-skill
- 创建/管理AuraDB实例 →
neo4j-aura-provisioning-skill - 创建向量索引 →
neo4j-vector-index-skill - 直接运行Cypher →
neo4j-cypher-skill - 构建Aura图分析会话 →
neo4j-aura-graph-analytics-skill
What are Aura Agents
什么是Aura Agents
GraphRAG agents on top of AuraDB — answer natural language questions via three tool types:
- CypherTemplate — parameterized queries for predictable lookups
- SimilaritySearch — vector similarity search over a VECTOR index
- Text2Cypher — natural language → Cypher for aggregations and discovery
Expose your graph via natural language to users or apps without application code. Accessible as REST or MCP endpoint; single- and multi-turn. For full Cypher control, low-latency lookups, or direct writes — use instead.
neo4j-cypher-skill基于AuraDB的GraphRAG代理——通过三种工具类型回答自然语言问题:
- CypherTemplate — 用于可预测查询的参数化查询语句
- SimilaritySearch — 在VECTOR索引上进行向量相似度搜索
- Text2Cypher — 将自然语言转换为Cypher语句,用于聚合和发现
无需编写应用代码,即可通过自然语言向用户或应用暴露你的图数据。可作为REST或MCP端点访问;支持单轮和多轮交互。如果需要完全控制Cypher、低延迟查询或直接写入操作,请改用。
neo4j-cypher-skillPrerequisites
前提条件
- Running AuraDB instance with knowledge graph loaded
- "Generative AI assistance" enabled in Organization settings
- "Aura Agent" toggled on in the project
- "Tool authentication" enabled at project/Security level
- Project admin access
- and
AURA_CLIENT_IDfrom console.neo4j.io → Account Settings → API CredentialsAURA_CLIENT_SECRET - ,
AURA_ORG_ID— see Step 2;AURA_PROJECT_ID— resolved interactively in Step 2 if not already setAURA_INSTANCE_ID - Python env: in skill directory (or
uv sync)pip install neo4j neo4j-graphrag requests python-dotenv - and
.envinschema.json.gitignore
- 运行中的AuraDB实例,且已加载知识图谱
- 组织设置中已启用“生成式AI辅助”
- 项目中已开启“Aura Agent”开关
- 项目/安全级别已启用“工具认证”
- 项目管理员权限
- 从console.neo4j.io → 账户设置 → API凭证获取和
AURA_CLIENT_IDAURA_CLIENT_SECRET - 、
AURA_ORG_ID— 参见步骤2;AURA_PROJECT_ID— 如果未预先设置,将在步骤2中交互式确定AURA_INSTANCE_ID - Python环境:在skill目录中执行(或执行
uv sync)pip install neo4j neo4j-graphrag requests python-dotenv - 和
.env已添加到schema.json.gitignore
Step 1 — Verify Auth
步骤1 — 验证认证
Manual credential verification only — scripts call internally.
get_token()bash
TOKEN=$(curl -s --request POST 'https://api.neo4j.io/oauth/token' \
--user "${AURA_CLIENT_ID}:${AURA_CLIENT_SECRET}" \
--header 'Content-Type: application/x-www-form-urlencoded' \
--data-urlencode 'grant_type=client_credentials' \
| jq -r '.access_token')
echo "Token: ${TOKEN:0:20}..."If blank token: verify / in . Stop and report.
Token TTL: 3600 s. Re-run on 401/403.
AURA_CLIENT_IDAURA_CLIENT_SECRET.env仅需手动验证凭证——脚本内部会调用。
get_token()bash
TOKEN=$(curl -s --request POST 'https://api.neo4j.io/oauth/token' \
--user "${AURA_CLIENT_ID}:${AURA_CLIENT_SECRET}" \
--header 'Content-Type: application/x-www-form-urlencoded' \
--data-urlencode 'grant_type=client_credentials' \
| jq -r '.access_token')
echo "Token: ${TOKEN:0:20}..."如果返回空令牌:检查中的/。停止操作并上报。
令牌有效期:3600秒。遇到401/403错误时重新执行此步骤。
.envAURA_CLIENT_IDAURA_CLIENT_SECRETStep 2 — Resolve Organization & Project IDs
步骤2 — 确定组织与项目ID
From console URL (fastest): open console.neo4j.io → navigate to a project. URL pattern:
/organizations/{AURA_ORG_ID}/projects/{AURA_PROJECT_ID}Programmatic fallback:
bash
curl -s https://api.neo4j.io/v1/tenants \
-H "Authorization: Bearer $TOKEN" | jq '.data[] | {id, name}'从控制台URL获取(最快方式):打开console.neo4j.io → 导航至某个项目。URL格式:
/organizations/{AURA_ORG_ID}/projects/{AURA_PROJECT_ID}程序化备选方案:
bash
curl -s https://api.neo4j.io/v1/tenants \
-H "Authorization: Bearer $TOKEN" | jq '.data[] | {id, name}'tenant id maps to AURA_PROJECT_ID
tenant id对应AURA_PROJECT_ID
Set in `.env`:AURA_ORG_ID=<organization-id>
AURA_PROJECT_ID=<project-id>
**Check `AURA_INSTANCE_ID`** — if it is already set in `.env`, skip the rest of this step.
If not set, list available instances and ask the user to choose:
```bash
curl -s "https://api.neo4j.io/v1/instances?tenantId=${AURA_PROJECT_ID}" \
-H "Authorization: Bearer $TOKEN" \
| jq '.data[] | {id, name, status, region, type}'Show output to user. Ask: "Which instance should the agent connect to?" Then write to :
.envAURA_INSTANCE_ID=<chosen-instance-id>
NEO4J_URI=neo4j+s://<chosen-instance-id>.databases.neo4j.ioIf the list is empty: no AuraDB instances exist in this project — an Aura Agent cannot be created without one. Stop and report.
If : re-run Step 1. If : verify . Stop and report.
401404AURA_PROJECT_ID
在`.env`中设置:AURA_ORG_ID=<organization-id>
AURA_PROJECT_ID=<project-id>
**检查`AURA_INSTANCE_ID`** — 如果已在`.env`中设置,跳过此步骤剩余部分。
如果未设置,列出可用实例并让用户选择:
```bash
curl -s "https://api.neo4j.io/v1/instances?tenantId=${AURA_PROJECT_ID}" \
-H "Authorization: Bearer $TOKEN" \
| jq '.data[] | {id, name, status, region, type}'将输出展示给用户。询问:“代理应连接到哪个实例?” 然后写入:
.envAURA_INSTANCE_ID=<chosen-instance-id>
NEO4J_URI=neo4j+s://<chosen-instance-id>.databases.neo4j.io如果实例列表为空:此项目中不存在AuraDB实例——没有AuraDB实例无法创建Aura Agent。停止操作并上报。
如果返回:重新执行步骤1。如果返回:验证。停止操作并上报。
401404AURA_PROJECT_IDStep 3 — List Existing Agents
步骤3 — 列出已有的代理
bash
uv run python3 scripts/manage_agent.py list # Linux/macOS
uv run python scripts\manage_agent.py list # WindowsOutput: agent IDs, names, enabled status, endpoint URLs.
If : re-run Step 1. If : verify /. Stop and report.
401404AURA_ORG_IDAURA_PROJECT_IDbash
uv run python3 scripts/manage_agent.py list # Linux/macOS
uv run python scripts\manage_agent.py list # Windows输出:代理ID、名称、启用状态、端点URL。
如果返回:重新执行步骤1。如果返回:验证/。停止操作并上报。
401404AURA_ORG_IDAURA_PROJECT_IDStep 4 — Fetch Graph Schema
步骤4 — 获取图模式
Requires , , in .
NEO4J_URINEO4J_USERNAMENEO4J_PASSWORD.envbash
uv run python3 scripts/fetch_schema.py # Linux/macOS
uv run python scripts\fetch_schema.py # WindowsSaves . Output: node/rel-type counts, node labels + typed properties (with Aura ), relationship patterns, VECTOR indexes.
schema.jsondata_typeData gate — script exits with error and does NOT write if:
schema.json- fewer than 2 nodes, OR
- zero relationship types
If gate fails: load data into the database before proceeding. Stop and report.
If : check uses ; instance must be . Stop and report.
If : . Stop and report.
ServiceUnavailableNEO4J_URIneo4j+s://runningneo4j-graphrag not founduv add neo4j-graphragRead before Step 5.
schema.json需要在中设置、、。
.envNEO4J_URINEO4J_USERNAMENEO4J_PASSWORDbash
uv run python3 scripts/fetch_schema.py # Linux/macOS
uv run python scripts\fetch_schema.py # Windows保存为。输出:节点/关系类型数量、节点标签+带类型的属性(包含Aura )、关系模式、VECTOR索引。
schema.jsondata_type数据校验 — 如果满足以下条件,脚本会报错退出且不会写入:
schema.json- 节点数量少于2个,或
- 关系类型数量为0
如果校验失败:先向数据库加载数据,再继续操作。停止操作并上报。
如果返回:检查是否使用;实例必须处于状态。停止操作并上报。
如果提示:执行。停止操作并上报。
ServiceUnavailableNEO4J_URIneo4j+s://runningneo4j-graphrag not founduv add neo4j-graphrag在步骤5之前阅读。
schema.jsonStep 5 — Discover Use Cases
步骤5 — 确定使用场景
Before designing tools, read references/authoring-guide.md.
Ask the user these questions. Do NOT guess tool types or parameters.
- "What questions should this agent answer?"
- "Which nodes or relationships matter most?" — match against
schema.json → node_props - "Do users search by a specific property value?" → CypherTemplate
- "Any counting, grouping, or date-range questions?" → Text2Cypher
- "Search for semantically similar text?" → check
schema.json → metadata → vector_index- No VECTOR index found: inform user; skip SimilaritySearch; delegate to first
neo4j-vector-index-skill - VECTOR index found: ask the user — "Which embedding provider and model should be used? What output dimension?" See supported models in . Do NOT guess or default.
references/REFERENCE.md → Embedding Provider Options
- No VECTOR index found: inform user; skip SimilaritySearch; delegate to
Tool selection:
| Use Case | Tool |
|---|---|
| Lookup by specific property value | |
| Semantic text search | |
| Aggregation, counting, open-ended | |
CypherTemplate parameters: for each parameter, read from or and use it as . If the property has , the parameter MUST list the valid values — copy them from the array in . Example: . Properties with are especially likely to be filter targets and must include valid values when low cardinality.
aura_data_typeschema.json → node_propsrel_propsdata_typelow_cardinality: truedescriptionvaluesschema.json"description": "Agreement type to filter by. Valid values: \"Distributor Agreement\", \"License Agreement\", \"NDA\""has_fulltext_index: trueSimilaritySearch configuration — ask the user for all three before drafting the tool config:
| Field | What to ask | Source |
|---|---|---|
| "openai" or "vertexai"? | User confirms |
| Which model? | User picks from |
| What output dimension? | Required if model is configurable (see table); fixed models use the table value |
indexnameschema.json → metadata → vector_indexstate = ONLINEdimensionvector.dimensionsSignals inventory: for each label or relationship that appears in a tool or the user's stated questions, write a signal block in the system prompt. See for the template and rules.
references/authoring-guide.md → Signals inventoryDraft config JSON → show to user for review → confirm → proceed to Step 6.
在设计工具之前,请阅读references/authoring-guide.md。
向用户询问以下问题。请勿猜测工具类型或参数。
- “此代理应回答哪些问题?”
- “哪些节点或关系最为重要?” — 与匹配
schema.json → node_props - “用户是否按特定属性值进行搜索?” → 使用CypherTemplate
- “是否有计数、分组或日期范围相关的问题?” → 使用Text2Cypher
- “是否需要搜索语义相似的文本?” → 检查
schema.json → metadata → vector_index- 未找到VECTOR索引:告知用户;跳过SimilaritySearch;先使用创建索引
neo4j-vector-index-skill - 找到VECTOR索引:询问用户 — “应使用哪个嵌入提供商和模型?输出维度是多少?” 参见中的支持模型。请勿猜测或使用默认值。
references/REFERENCE.md → Embedding Provider Options
- 未找到VECTOR索引:告知用户;跳过SimilaritySearch;先使用
工具选择:
| 使用场景 | 工具 |
|---|---|
| 按特定属性值查询 | |
| 语义文本搜索 | |
| 聚合、计数、开放式问题 | |
CypherTemplate参数:对于每个参数,从或中读取并将其用作。如果属性的,参数的必须列出有效值——从的数组中复制。示例:。带有的属性尤其适合作为筛选目标,且当基数较低时必须包含有效值。
schema.json → node_propsrel_propsaura_data_typedata_typelow_cardinality: truedescriptionschema.jsonvalues"description": "要筛选的协议类型。有效值:\"Distributor Agreement\", \"License Agreement\", \"NDA\""has_fulltext_index: trueSimilaritySearch配置 — 在起草工具配置之前,向用户询问以下三项:
| 字段 | 询问内容 | 来源 |
|---|---|---|
| 使用“openai”还是“vertexai”? | 用户确认 |
| 使用哪个模型? | 用户从 |
| 输出维度是多少? | 如果模型可配置则必填(参见表格);固定模型使用表格中的值 |
indexschema.json → metadata → vector_indexstate = ONLINEnamedimensionvector.dimensions信号清单:对于工具或用户提出的问题中出现的每个标签或关系,在系统提示中写入一个信号块。模板和规则参见。
references/authoring-guide.md → Signals inventory起草配置JSON → 展示给用户审核 → 确认 → 进入步骤6。
Step 6 — Create Agent
步骤6 — 创建代理
Minimum required config:
json
{
"name": "My Agent",
"description": "Answers questions about the graph",
"dbid": "<AURA_INSTANCE_ID>",
"is_private": false,
"tools": [
{
"type": "text2cypher",
"name": "Query Graph",
"description": "Translates natural language questions into Cypher queries"
}
]
}Show config to user and confirm before running:
bash
uv run python3 scripts/manage_agent.py create --config agent-config.jsonResponse includes (save as ), , .
idAURA_AGENT_IDendpoint_linkmcp_endpoint_link最小必填配置:
json
{
"name": "My Agent",
"description": "Answers questions about the graph",
"dbid": "<AURA_INSTANCE_ID>",
"is_private": false,
"tools": [
{
"type": "text2cypher",
"name": "Query Graph",
"description": "Translates natural language questions into Cypher queries"
}
]
}运行前展示配置并获得用户确认:
bash
uv run python3 scripts/manage_agent.py create --config agent-config.json响应包含(保存为)、、。
idAURA_AGENT_IDendpoint_linkmcp_endpoint_linkStep 7 — Invoke Agent (Test)
步骤7 — 调用代理(测试)
bash
uv run python3 scripts/invoke_agent.py --agent-id "$AURA_AGENT_ID" "What can you help me with?"--rawDirect curl (uses token from Step 1):
bash
curl -s -X POST \
"https://api.neo4j.io/v2beta1/organizations/${AURA_ORG_ID}/projects/${AURA_PROJECT_ID}/agents/${AURA_AGENT_ID}/invoke" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-d '{"input": "What can you help me with?"}'bash
uv run python3 scripts/invoke_agent.py --agent-id "$AURA_AGENT_ID" "What can you help me with?"--raw直接使用curl调用(使用步骤1中的令牌):
bash
curl -s -X POST \
"https://api.neo4j.io/v2beta1/organizations/${AURA_ORG_ID}/projects/${AURA_PROJECT_ID}/agents/${AURA_AGENT_ID}/invoke" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-d '{"input": "What can you help me with?"}'Step 8 — Update Agent (Partial PATCH)
步骤8 — 更新代理(部分PATCH)
Create patch JSON with only the fields to change:
json
{ "system_prompt": "Updated instructions.", "is_mcp_enabled": true }Show to user and confirm before running:
bash
uv run python3 scripts/manage_agent.py update --agent-id "$AURA_AGENT_ID" --config patch.json创建仅包含需修改字段的补丁JSON:
json
{ "system_prompt": "Updated instructions.", "is_mcp_enabled": true }运行前展示给用户并获得确认:
bash
uv run python3 scripts/manage_agent.py update --agent-id "$AURA_AGENT_ID" --config patch.jsonStep 9 — Delete Agent
步骤9 — 删除代理
IRREVERSIBLE. Configuration permanently removed.
Show to user and wait for explicit confirmation before running:
bash
uv run python3 scripts/manage_agent.py delete --agent-id "$AURA_AGENT_ID"Returns 202 Accepted.
此操作不可撤销。配置将被永久移除。
运行前展示给用户并等待明确确认:
bash
uv run python3 scripts/manage_agent.py delete --agent-id "$AURA_AGENT_ID"返回202 Accepted.
Tool Configuration
工具配置
CypherTemplate
CypherTemplate
Pre-defined parameterized queries for repeated, predictable lookups.
json
{
"type": "cypherTemplate",
"name": "<descriptive name>",
"description": "<what it looks up and when to use it>",
"enabled": true,
"config": {
"template": "MATCH (n:Label {prop: $param}) RETURN n",
"parameters": [
{
"name": "param",
"data_type": "<string|integer|number|boolean — from schema.json aura_data_type>",
"description": "<what the parameter represents. If low_cardinality=true in schema.json, append: Valid values: \"val1\", \"val2\", ...>"
}
]
}
}Low-cardinality rule: if is , the field must end with the exact values from . This applies to relationship properties in too.
schema.json → node_props[Label][prop].low_cardinalitytruedescriptionschema.json → node_props[Label][prop].valuesrel_props用于重复、可预测查询的预定义参数化查询语句。
json
{
"type": "cypherTemplate",
"name": "<descriptive name>",
"description": "<what it looks up and when to use it>",
"enabled": true,
"config": {
"template": "MATCH (n:Label {prop: $param}) RETURN n",
"parameters": [
{
"name": "param",
"data_type": "<string|integer|number|boolean — from schema.json aura_data_type>",
"description": "<what the parameter represents. If low_cardinality=true in schema.json, append: Valid values: \"val1\", \"val2\", ...>"
}
]
}
}低基数规则:如果为,字段必须以中的精确值结尾。此规则同样适用于中的关系属性。
schema.json → node_props[Label][prop].low_cardinalitytruedescriptionschema.json → node_props[Label][prop].valuesrel_propsSimilaritySearch
SimilaritySearch
Requires a VECTOR index (). Get index name from .
state = ONLINEschema.json → metadata → vector_indexjson
{
"type": "similaritySearch",
"name": "<descriptive name>",
"description": "<what text it searches and when to use it>",
"enabled": true,
"config": {
"provider": "openai",
"model": "text-embedding-3-small",
"index": "<name from schema.json metadata.vector_index[state=ONLINE].name>",
"top_k": 5,
"dimension": "<vector.dimensions from schema.json metadata.vector_index options.indexConfig>",
"post_processing_cypher": "<optional: Cypher to enrich similarity results with related nodes>"
}
}providermodel需要VECTOR索引()。从获取索引名称。
state = ONLINEschema.json → metadata → vector_indexjson
{
"type": "similaritySearch",
"name": "<descriptive name>",
"description": "<what text it searches and when to use it>",
"enabled": true,
"config": {
"provider": "openai",
"model": "text-embedding-3-small",
"index": "<name from schema.json metadata.vector_index[state=ONLINE].name>",
"top_k": 5,
"dimension": "<vector.dimensions from schema.json metadata.vector_index options.indexConfig>",
"post_processing_cypher": "<optional: Cypher to enrich similarity results with related nodes>"
}
}providermodelText2Cypher
Text2Cypher
Natural language → Cypher. Use as fallback for aggregation and discovery.
json
{
"type": "text2cypher",
"name": "<descriptive name>",
"description": "<what questions it handles — and explicitly what it should NOT handle>",
"enabled": true
}自然语言转Cypher。用作聚合和发现场景的备选方案。
json
{
"type": "text2cypher",
"name": "<descriptive name>",
"description": "<what questions it handles — and explicitly what it should NOT handle>",
"enabled": true
}Common Errors
常见错误
| Error | Cause | Fix |
|---|---|---|
| Token expired | Re-run Step 1 |
| Not a project admin | Request admin access |
| Invalid tool config or missing required field | Check |
| Wrong org/project/agent ID | Re-run |
| Vector index missing | Create index first — use |
| Agent returns no results | | Increase |
| 错误 | 原因 | 修复方案 |
|---|---|---|
| 令牌过期 | 重新执行步骤1 |
创建时返回 | 非项目管理员 | 请求管理员权限 |
| 工具配置无效或缺少必填字段 | 检查 |
| 组织/项目/代理ID错误 | 重新执行 |
使用SimilaritySearch创建时返回 | 缺少向量索引 | 先创建索引——使用 |
| 代理无结果返回 | | 增大 |
Scripts
脚本
All scripts load credentials from automatically. Run with .
.envuv run python3 <script>| Script | Purpose |
|---|---|
| Fetch graph schema from AuraDB; save to |
| CRUD: list, create, get, update, delete agents |
| Send a natural language query to an agent |
fetch_schema.py parameters:
| Parameter | Type | Required | Default |
|---|---|---|---|
| env | Yes | — |
| env | No | |
| env | Yes | — |
| env | No | |
manage_agent.py parameters:
| Parameter | Type | Required | Env fallback |
|---|---|---|---|
| env | Yes | — |
| env | Yes | — |
| arg | No | |
| arg | No | |
| arg | get/update/delete | |
| arg | create/update | — |
invoke_agent.py parameters:
| Parameter | Type | Required | Env fallback |
|---|---|---|---|
| env | Yes | — |
| env | Yes | — |
| arg | No | |
| arg | No | |
| arg | Yes | |
| positional | Yes | — |
| flag | No | — |
所有脚本会自动从加载凭证。使用运行。
.envuv run python3 <script>| 脚本 | 用途 |
|---|---|
| 从AuraDB获取图模式;保存为 |
| CRUD操作:列出、创建、获取、更新、删除代理 |
| 向代理发送自然语言查询 |
fetch_schema.py参数:
| 参数 | 类型 | 必填 | 默认值 |
|---|---|---|---|
| 环境变量 | 是 | — |
| 环境变量 | 否 | |
| 环境变量 | 是 | — |
| 环境变量 | 否 | |
manage_agent.py参数:
| 参数 | 类型 | 必填 | 环境变量备选值 |
|---|---|---|---|
| 环境变量 | 是 | — |
| 环境变量 | 是 | — |
| 参数 | 否 | |
| 参数 | 否 | |
| 参数 | get/update/delete操作必填 | |
| 参数 | create/update操作必填 | — |
invoke_agent.py参数:
| 参数 | 类型 | 必填 | 环境变量备选值 |
|---|---|---|---|
| 环境变量 | 是 | — |
| 环境变量 | 是 | — |
| 参数 | 否 | |
| 参数 | 否 | |
| 参数 | 是 | |
| 位置参数 | 是 | — |
| 标志参数 | 否 | — |
Checklist
检查清单
- AuraDB instance , knowledge graph loaded
running - "Generative AI assistance" + "Aura Agent" enabled in org/project settings
- populated:
.env,AURA_CLIENT_ID,AURA_CLIENT_SECRET,AURA_ORG_ID,AURA_PROJECT_ID,AURA_INSTANCE_ID,NEO4J_URINEO4J_PASSWORD - and
.envinschema.json.gitignore - Auth verified (Step 1)
- Org/Project IDs confirmed (Step 2)
- API connectivity confirmed via (Step 3)
list - fetched and reviewed (Step 4) — data gate passed (≥2 nodes, ≥1 rel type)
schema.json - Use cases confirmed with user (Step 5)
- CypherTemplate taken from
data_typeschema.json aura_data_type - SimilaritySearch from
index(state=ONLINE)schema.json metadata.vector_index - Agent config shown to user and confirmed (Step 6)
- Required fields present: ,
name,description,dbid,is_private(min 1)tools - saved from create response
AURA_AGENT_ID - Agent invoked and response verified (Step 7)
- Update/Delete confirmed by user before execution
- AuraDB实例处于状态,且已加载知识图谱
running - 组织/项目设置中已启用“生成式AI辅助”+“Aura Agent”
- 已填充:
.env,AURA_CLIENT_ID,AURA_CLIENT_SECRET,AURA_ORG_ID,AURA_PROJECT_ID,AURA_INSTANCE_ID,NEO4J_URINEO4J_PASSWORD - 和
.env已添加到schema.json.gitignore - 已完成认证验证(步骤1)
- 已确认组织/项目ID(步骤2)
- 通过命令确认API连通性(步骤3)
list - 已获取并查看(步骤4)——通过数据校验(≥2个节点,≥1种关系类型)
schema.json - 已与用户确认使用场景(步骤5)
- CypherTemplate的取自
data_typeschema.json aura_data_type - SimilaritySearch的取自
index(state=ONLINE)schema.json metadata.vector_index - 已向用户展示代理配置并获得确认(步骤6)
- 必填字段齐全:,
name,description,dbid,is_private(至少1个)tools - 已从创建响应中保存
AURA_AGENT_ID - 已调用代理并验证响应(步骤7)
- 更新/删除操作已获得用户确认后执行