Refactor: text2germlin with PCgraph framework#50
Refactor: text2germlin with PCgraph framework#50weijinglin merged 9 commits intohugegraph:agenticrag/devfrom
Conversation
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the Note Other AI code review bot(s) detectedCodeRabbit has detected other AI code review bot(s) in this pull request and will avoid duplicating their findings in the review comments. This may lead to a less comprehensive review. Walkthrough本次变更在现有 RAG/演示代码大量格式化调整的同时，引入了“Text2Gremlin”新流程：新增流与节点、扩展状态模型、接入调度器，并在 API 与 Gradio UI 中使用该流程；同时扩展多项配置与请求模型字段，少量行为性改动包含输入校验、执行结果回传及关键词抽取过滤。 Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor U as 前端/Gradio UI
participant API as 后端API(text2gremlin_api)
participant S as SchedulerSingleton
participant F as Text2GremlinFlow
participant N1 as SchemaNode
participant N2 as GremlinExampleIndexQueryNode
participant N3 as Text2GremlinNode
participant N4 as GremlinExecuteNode
participant LLM as LLM
participant HG as HugeGraph
U->>API: POST /text2gremlin (query, example_num, prompt, outputs)
alt 空查询
API-->>U: 400 Bad Request
else 正常
API->>S: schedule_flow("text2gremlin", params)
S->>F: 构建并reset状态
F->>N1: 载入/规范化 schema
N1-->>F: schema
F->>N2: 示例匹配(query, example_num)
N2-->>F: match_result
F->>N3: 生成 template/raw Gremlin
N3->>LLM: 文本转Gremlin提示词
LLM-->>N3: 生成结果
N3-->>F: 模板/原始 Gremlin
F->>N4: 按请求键执行 Gremlin
N4->>HG: 执行 template/raw Gremlin(带默认limit)
HG-->>N4: 执行结果/错误
N4-->>F: 写入执行结果
F-->>S: 聚合输出
S-->>API: 返回结果字典
API-->>U: 200 含 match/template/raw/执行结果
end
sequenceDiagram
autonumber
actor U as 前端/Gradio UI
participant API as 后端API
participant S as Scheduler
note over API,S: 错误路径（调度/执行异常）
U->>API: 请求
API->>S: 调度执行
S--xAPI: 抛出异常(记录错误)
API-->>U: 500 Internal Server Error / UI 捕获并提示
Estimated code review effort🎯 4 (复杂) | ⏱️ ~60 minutes Possibly related PRs
Poem
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
Tip 👮 Agentic pre-merge checks are now available in preview!Pro plan users can now enable pre-merge checks in their settings to enforce checklists before merging PRs.
Please see the documentation for more information. Example: reviews:
pre_merge_checks:
custom_checks:
- name: "Undocumented Breaking Changes"
mode: "warning"
instructions: |
Pass/fail criteria: All breaking changes to public APIs, CLI flags, environment variables, configuration keys, database schemas, or HTTP/GraphQL endpoints must be documented in the "Breaking Change" section of the PR description and in CHANGELOG.md. Exclude purely internal or private changes (e.g., code not exported from package entry points or explicitly marked as internal).Please share your feedback with us on this Discord post. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
@codecov-ai-reviewer review |
There was a problem hiding this comment.
Pull Request Overview
This PR refactors the text2gremlin functionality to use the PCgraph framework, migrating from a direct implementation to a node-based pipeline architecture. The refactor introduces standardized workflow management and improves modularity by breaking down text2gremlin processing into discrete, reusable nodes.
Key changes:
- Introduces new node classes for text2gremlin pipeline components (Text2GremlinNode, GremlinExampleIndexQueryNode, GremlinExecuteNode)
- Creates a Text2GremlinFlow class that orchestrates the entire text2gremlin workflow
- Updates the scheduler to support the new text2gremlin flow
- Modifies existing API and demo code to use the new pipeline-based approach
Reviewed Changes
Copilot reviewed 9 out of 9 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| ai_state.py | Adds Text2Gremlin-specific fields to workflow input and state classes |
| text2gremlin.py | New node class for LLM-based Gremlin query generation |
| gremlin_example_index_query.py | New node class for querying Gremlin examples from index |
| schema.py | Replaces debug print with proper logging |
| gremlin_execute.py | New node class for executing generated Gremlin queries |
| text2gremlin.py (flow) | New flow class orchestrating the complete text2gremlin pipeline |
| scheduler.py | Integrates text2gremlin flow and adds state reset functionality |
| text2gremlin_block.py | Updates demo code to use new scheduler-based approach |
| rag_api.py | Updates API endpoint to use new scheduler-based approach |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
|
@codecov-ai-reviewer review |
|
@fantasy-lotus I'll perform a comprehensive full review of all changes in this PR that refactors text2gremlin with the PCgraph framework. ✅ Actions performedFull review triggered. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (5)
hugegraph-llm/src/hugegraph_llm/operators/llm_op/keyword_extract.py (1)
91-94: 请恢复对单字符关键词的支持这里新增的
len(k.strip()) > 1过滤会直接丢弃所有单字符关键词。对于中文场景（如“图”“数”）以及仅由单字符缩写构成的英文关键词（如“C”“R”）来说，这是合法且常见的输出，会导致提取结果缺失。建议仅过滤掉空字符串等无效结果。- if len(k.strip()) > 1 + if k.strip()hugegraph-llm/src/hugegraph_llm/middleware/middleware.py (1)
37-45: 修正日志单位与数值不一致当
process_time > 1000时，变量已经换算为秒，但日志仍然写死为 “ms”，会导致运维观测时误判耗时。请保持日志输出的单位与数值一致。- process_time = (time.perf_counter() - start_time) * 1000 # ms - unit = "ms" - if process_time > 1000: - process_time /= 1000 - unit = "s" + process_time_ms = (time.perf_counter() - start_time) * 1000 + process_time = process_time_ms + unit = "ms" + if process_time_ms > 1000: + process_time = process_time_ms / 1000 + unit = "s" response.headers["X-Process-Time"] = f"{process_time:.2f} {unit}" - log.info("Request process time: %.2f ms, code=%d", process_time, response.status_code) + log.info("Request process time: %.2f %s, code=%d", process_time, unit, response.status_code)hugegraph-llm/src/hugegraph_llm/nodes/hugegraph_node/schema.py (1)
18-18: 修复 PyCGraph.CStatus 导入错误GitHub Actions 的 pylint 报告
E0611: No name 'CStatus' in module 'PyCGraph'，流水线当前因此失败。请确认 PyCGraph 实际暴露的符号名称（或补充类型定义/忽略配置），并调整这里的导入或依赖版本，以确保 lint 和运行时都能正确加载。hugegraph-llm/src/hugegraph_llm/indices/vector_index.py (1)
138-147: 修复 Faiss 返回 -1 时的错误命中Faiss 在找不到足够邻居时会返回索引
-1，目前的实现会把它当作合法索引并取列表最后一个元素，直接导致检索结果被污染。建议按如下方式跳过占位索引：
- for dist, i in zip(distances[0], indices[0]): - if dist < dis_threshold: # Smaller distances indicate higher similarity + for dist, i in zip(distances[0], indices[0]): + if i == -1: + log.debug("Faiss returned placeholder index -1, skip this candidate.") + continue + if dist < dis_threshold: # Smaller distances indicate higher similarity results.append(deepcopy(self.properties[i])) log.debug("[✓] Add valid distance %s to results.", dist) else:hugegraph-llm/src/hugegraph_llm/state/ai_state.py (1)
16-16: 同步处理 PyCGraph 导入的 pylint 误报这里同样触发了
E0611: No name 'GParam' in module 'PyCGraph'和E0611: No name 'CStatus' in module 'PyCGraph'，目前 CI 已经失败。建议参照其它位置在导入行增加忽略标记，保证流水线能通过，例如：-from PyCGraph import GParam, CStatus +from PyCGraph import GParam, CStatus # pylint: disable=import-error请一并修正。
🧹 Nitpick comments (4)
hugegraph-python-client/src/pyhugegraph/api/schema.py (2)
85-89: 日志中请包含请求的标签名
当前的错误日志输出str(response)，在未找到时 response 通常是 None，信息量有限，并且导致我们不得不保留# pylint: disable=unused-argument。建议直接记录请求的name，既能提供准确的排查信息，也能移除这条 pylint 忽略。- def getVertexLabel(self, name) -> Optional[VertexLabelData]: # pylint: disable=unused-argument + def getVertexLabel(self, name) -> Optional[VertexLabelData]: if response := self._invoke_request(): return VertexLabelData(response) - log.error("VertexLabel not found: %s", str(response)) + log.error("VertexLabel not found: %s", name) return None
127-131: 错误日志应指向索引名称
当前在失败路径下打印的是str(response)，实际多为 None，不利于迅速定位问题，也迫使我们保留# pylint: disable=unused-argument。建议直接记录请求的name，并删除这条 pylint 忽略。- def getIndexLabel(self, name) -> Optional[IndexLabelData]: # pylint: disable=unused-argument + def getIndexLabel(self, name) -> Optional[IndexLabelData]: if response := self._invoke_request(): return IndexLabelData(response) - log.error("IndexLabel not found: %s", str(response)) + log.error("IndexLabel not found: %s", name) return Nonehugegraph-llm/src/hugegraph_llm/operators/llm_op/schema_build.py (1)
88-123: 统一query_examples的类型契约
build_prompt()的类型注解仍然是List[Dict[str, str]]，Docstring 也写明每个示例要包含 “description + Gremlin”，但run()新增的校验与报错信息却假定传入的是list[str]。这会让调用方和类型检查工具拿不准到底该传什么结构，一旦后续在 PCGraph 流里继续传 dict，就会被误导成输入格式错误。建议尽快统一约定：要么将 prompt 构造逻辑彻底切换成接收list[str]并同步更新类型注解、文档和元素校验；要么（更符合 “description + Gremlin” 的语义）在这里校验每个元素是包含所需字段的 dict，并把错误信息改成反映真实期望的结构。hugegraph-llm/src/hugegraph_llm/utils/decorators.py (1)
117-123: 任务ID没有写回上下文当前逻辑只在返回值拥有
__closure__且为真时才写入task_id，但装饰的函数通常返回dict或一般对象，这个分支几乎不会命中，导致下游无法读取到我们刚生成的任务 ID。建议直接在常见返回类型（例如dict）上补齐写入逻辑，同时保留对可设置属性对象的兼容。# Store the original return value result = func(*args, **kwargs) # Add the task_id to the function's context - if hasattr(result, "__closure__") and result.__closure__: - # If it's a closure, we can add the task_id to its context - setattr(result, "task_id", task_id) + if isinstance(result, dict): + result.setdefault("task_id", task_id) + elif hasattr(result, "__dict__"): + setattr(result, "task_id", task_id) + elif hasattr(result, "__closure__") and result.__closure__: + setattr(result, "task_id", task_id) return result
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (94)
hugegraph-llm/src/hugegraph_llm/api/admin_api.py(1 hunks)hugegraph-llm/src/hugegraph_llm/api/exceptions/rag_exceptions.py(1 hunks)hugegraph-llm/src/hugegraph_llm/api/models/rag_requests.py(4 hunks)hugegraph-llm/src/hugegraph_llm/api/rag_api.py(8 hunks)hugegraph-llm/src/hugegraph_llm/config/admin_config.py(1 hunks)hugegraph-llm/src/hugegraph_llm/config/generate.py(1 hunks)hugegraph-llm/src/hugegraph_llm/config/hugegraph_config.py(1 hunks)hugegraph-llm/src/hugegraph_llm/config/llm_config.py(1 hunks)hugegraph-llm/src/hugegraph_llm/config/models/base_config.py(3 hunks)hugegraph-llm/src/hugegraph_llm/config/models/base_prompt_config.py(4 hunks)hugegraph-llm/src/hugegraph_llm/config/prompt_config.py(1 hunks)hugegraph-llm/src/hugegraph_llm/demo/rag_demo/admin_block.py(7 hunks)hugegraph-llm/src/hugegraph_llm/demo/rag_demo/app.py(1 hunks)hugegraph-llm/src/hugegraph_llm/demo/rag_demo/configs_block.py(17 hunks)hugegraph-llm/src/hugegraph_llm/demo/rag_demo/other_block.py(2 hunks)hugegraph-llm/src/hugegraph_llm/demo/rag_demo/rag_block.py(11 hunks)hugegraph-llm/src/hugegraph_llm/demo/rag_demo/text2gremlin_block.py(10 hunks)hugegraph-llm/src/hugegraph_llm/demo/rag_demo/vector_graph_block.py(10 hunks)hugegraph-llm/src/hugegraph_llm/document/chunk_split.py(2 hunks)hugegraph-llm/src/hugegraph_llm/flows/get_graph_index_info.py(1 hunks)hugegraph-llm/src/hugegraph_llm/flows/graph_extract.py(1 hunks)hugegraph-llm/src/hugegraph_llm/flows/import_graph_data.py(1 hunks)hugegraph-llm/src/hugegraph_llm/flows/prompt_generate.py(1 hunks)hugegraph-llm/src/hugegraph_llm/flows/scheduler.py(3 hunks)hugegraph-llm/src/hugegraph_llm/flows/text2gremlin.py(1 hunks)hugegraph-llm/src/hugegraph_llm/indices/graph_index.py(1 hunks)hugegraph-llm/src/hugegraph_llm/indices/vector_index.py(6 hunks)hugegraph-llm/src/hugegraph_llm/middleware/middleware.py(2 hunks)hugegraph-llm/src/hugegraph_llm/models/embeddings/base.py(5 hunks)hugegraph-llm/src/hugegraph_llm/models/embeddings/openai.py(4 hunks)hugegraph-llm/src/hugegraph_llm/models/llms/base.py(1 hunks)hugegraph-llm/src/hugegraph_llm/models/llms/init_llm.py(1 hunks)hugegraph-llm/src/hugegraph_llm/models/llms/litellm.py(2 hunks)hugegraph-llm/src/hugegraph_llm/models/llms/ollama.py(6 hunks)hugegraph-llm/src/hugegraph_llm/models/llms/openai.py(2 hunks)hugegraph-llm/src/hugegraph_llm/models/rerankers/cohere.py(1 hunks)hugegraph-llm/src/hugegraph_llm/models/rerankers/init_reranker.py(1 hunks)hugegraph-llm/src/hugegraph_llm/models/rerankers/siliconflow.py(2 hunks)hugegraph-llm/src/hugegraph_llm/nodes/hugegraph_node/gremlin_execute.py(1 hunks)hugegraph-llm/src/hugegraph_llm/nodes/hugegraph_node/schema.py(1 hunks)hugegraph-llm/src/hugegraph_llm/nodes/index_node/gremlin_example_index_query.py(1 hunks)hugegraph-llm/src/hugegraph_llm/nodes/llm_node/schema_build.py(1 hunks)hugegraph-llm/src/hugegraph_llm/nodes/llm_node/text2gremlin.py(1 hunks)hugegraph-llm/src/hugegraph_llm/operators/common_op/check_schema.py(4 hunks)hugegraph-llm/src/hugegraph_llm/operators/common_op/merge_dedup_rerank.py(2 hunks)hugegraph-llm/src/hugegraph_llm/operators/document_op/word_extract.py(1 hunks)hugegraph-llm/src/hugegraph_llm/operators/graph_rag_task.py(2 hunks)hugegraph-llm/src/hugegraph_llm/operators/hugegraph_op/commit_to_hugegraph.py(10 hunks)hugegraph-llm/src/hugegraph_llm/operators/hugegraph_op/graph_rag_query.py(10 hunks)hugegraph-llm/src/hugegraph_llm/operators/hugegraph_op/schema_manager.py(1 hunks)hugegraph-llm/src/hugegraph_llm/operators/index_op/build_gremlin_example_index.py(1 hunks)hugegraph-llm/src/hugegraph_llm/operators/index_op/build_semantic_index.py(2 hunks)hugegraph-llm/src/hugegraph_llm/operators/index_op/build_vector_index.py(1 hunks)hugegraph-llm/src/hugegraph_llm/operators/index_op/gremlin_example_index_query.py(2 hunks)hugegraph-llm/src/hugegraph_llm/operators/index_op/semantic_id_query.py(4 hunks)hugegraph-llm/src/hugegraph_llm/operators/index_op/vector_index_query.py(1 hunks)hugegraph-llm/src/hugegraph_llm/operators/kg_construction_task.py(2 hunks)hugegraph-llm/src/hugegraph_llm/operators/llm_op/answer_synthesize.py(5 hunks)hugegraph-llm/src/hugegraph_llm/operators/llm_op/disambiguate_data.py(1 hunks)hugegraph-llm/src/hugegraph_llm/operators/llm_op/gremlin_generate.py(3 hunks)hugegraph-llm/src/hugegraph_llm/operators/llm_op/info_extract.py(1 hunks)hugegraph-llm/src/hugegraph_llm/operators/llm_op/keyword_extract.py(3 hunks)hugegraph-llm/src/hugegraph_llm/operators/llm_op/prompt_generate.py(1 hunks)hugegraph-llm/src/hugegraph_llm/operators/llm_op/property_graph_extract.py(4 hunks)hugegraph-llm/src/hugegraph_llm/operators/llm_op/schema_build.py(3 hunks)hugegraph-llm/src/hugegraph_llm/state/ai_state.py(5 hunks)hugegraph-llm/src/hugegraph_llm/utils/anchor.py(1 hunks)hugegraph-llm/src/hugegraph_llm/utils/decorators.py(1 hunks)hugegraph-llm/src/hugegraph_llm/utils/embedding_utils.py(2 hunks)hugegraph-llm/src/hugegraph_llm/utils/graph_index_utils.py(7 hunks)hugegraph-llm/src/hugegraph_llm/utils/hugegraph_utils.py(4 hunks)hugegraph-llm/src/hugegraph_llm/utils/log.py(1 hunks)hugegraph-llm/src/hugegraph_llm/utils/vector_index_utils.py(3 hunks)hugegraph-llm/src/tests/config/test_config.py(1 hunks)hugegraph-llm/src/tests/models/embeddings/test_openai_embedding.py(1 hunks)hugegraph-llm/src/tests/models/llms/test_ollama_client.py(1 hunks)hugegraph-llm/src/tests/operators/common_op/test_check_schema.py(2 hunks)hugegraph-llm/src/tests/operators/common_op/test_nltk_helper.py(1 hunks)hugegraph-python-client/src/pyhugegraph/api/auth.py(4 hunks)hugegraph-python-client/src/pyhugegraph/api/graph.py(1 hunks)hugegraph-python-client/src/pyhugegraph/api/schema.py(3 hunks)hugegraph-python-client/src/pyhugegraph/api/schema_manage/index_label.py(1 hunks)hugegraph-python-client/src/pyhugegraph/api/services.py(2 hunks)hugegraph-python-client/src/pyhugegraph/api/traverser.py(5 hunks)hugegraph-python-client/src/pyhugegraph/client.py(1 hunks)hugegraph-python-client/src/pyhugegraph/example/hugegraph_example.py(2 hunks)hugegraph-python-client/src/pyhugegraph/structure/property_key_data.py(1 hunks)hugegraph-python-client/src/pyhugegraph/utils/huge_config.py(2 hunks)hugegraph-python-client/src/pyhugegraph/utils/huge_router.py(2 hunks)hugegraph-python-client/src/pyhugegraph/utils/log.py(1 hunks)hugegraph-python-client/src/pyhugegraph/utils/util.py(3 hunks)hugegraph-python-client/src/tests/api/test_auth.py(2 hunks)hugegraph-python-client/src/tests/api/test_version.py(1 hunks)hugegraph-python-client/src/tests/client_utils.py(1 hunks)
🧰 Additional context used
🧠 Learnings (19)
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/src/hugegraph_llm/indices/**/*.py : Store vector and graph indexing code under src/hugegraph_llm/indices/
Applied to files:
hugegraph-llm/src/hugegraph_llm/operators/index_op/vector_index_query.pyhugegraph-llm/src/hugegraph_llm/operators/index_op/build_vector_index.pyhugegraph-llm/src/hugegraph_llm/indices/graph_index.pyhugegraph-llm/src/hugegraph_llm/utils/vector_index_utils.pyhugegraph-llm/src/hugegraph_llm/utils/graph_index_utils.pyhugegraph-llm/src/hugegraph_llm/indices/vector_index.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/src/hugegraph_llm/operators/gremlin_generate_task.py : Maintain the Text2Gremlin pipeline in src/hugegraph_llm/operators/gremlin_generate_task.py
Applied to files:
hugegraph-llm/src/hugegraph_llm/operators/llm_op/gremlin_generate.pyhugegraph-llm/src/hugegraph_llm/flows/scheduler.pyhugegraph-llm/src/hugegraph_llm/api/rag_api.pyhugegraph-llm/src/hugegraph_llm/operators/index_op/build_gremlin_example_index.pyhugegraph-llm/src/hugegraph_llm/operators/index_op/gremlin_example_index_query.pyhugegraph-llm/src/hugegraph_llm/operators/graph_rag_task.pyhugegraph-llm/src/hugegraph_llm/nodes/index_node/gremlin_example_index_query.pyhugegraph-llm/src/hugegraph_llm/demo/rag_demo/text2gremlin_block.pyhugegraph-llm/src/hugegraph_llm/nodes/hugegraph_node/gremlin_execute.pyhugegraph-llm/src/hugegraph_llm/flows/text2gremlin.pyhugegraph-llm/src/hugegraph_llm/nodes/llm_node/text2gremlin.pyhugegraph-llm/src/hugegraph_llm/state/ai_state.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/src/hugegraph_llm/demo/rag_demo/**/*.py : Implement the Gradio UI application under src/hugegraph_llm/demo/rag_demo/
Applied to files:
hugegraph-llm/src/hugegraph_llm/demo/rag_demo/admin_block.pyhugegraph-llm/src/hugegraph_llm/api/rag_api.pyhugegraph-llm/src/hugegraph_llm/demo/rag_demo/configs_block.pyhugegraph-llm/src/hugegraph_llm/demo/rag_demo/app.pyhugegraph-llm/src/hugegraph_llm/demo/rag_demo/rag_block.pyhugegraph-llm/src/hugegraph_llm/demo/rag_demo/vector_graph_block.py
📚 Learning: 2025-08-18T14:37:41.224Z
Learnt from: Gfreely
PR: hugegraph/hugegraph-ai#32
File: hugegraph-llm/src/hugegraph_llm/operators/document_op/textrank_word_extract.py:139-141
Timestamp: 2025-08-18T14:37:41.224Z
Learning: In hugegraph-llm textrank_word_extract.py, NLTK resources are packaged locally under src/hugegraph_llm/resources/nltk_data/ and the code properly configures nltk.data.path using get_project_root() to point to these local resources before making NLTK calls, preventing LookupError issues.
Applied to files:
hugegraph-llm/src/tests/config/test_config.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/src/hugegraph_llm/operators/graph_rag_task.py : Maintain the Graph RAG pipeline in src/hugegraph_llm/operators/graph_rag_task.py
Applied to files:
hugegraph-llm/src/hugegraph_llm/api/rag_api.pyhugegraph-llm/src/hugegraph_llm/operators/hugegraph_op/graph_rag_query.pyhugegraph-llm/src/hugegraph_llm/operators/graph_rag_task.pyhugegraph-llm/src/hugegraph_llm/demo/rag_demo/vector_graph_block.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/src/hugegraph_llm/operators/kg_construction_task.py : Maintain the KG Construction pipeline in src/hugegraph_llm/operators/kg_construction_task.py
Applied to files:
hugegraph-llm/src/hugegraph_llm/operators/kg_construction_task.pyhugegraph-llm/src/hugegraph_llm/operators/graph_rag_task.pyhugegraph-llm/src/hugegraph_llm/utils/graph_index_utils.py
📚 Learning: 2025-06-25T09:50:06.213Z
Learnt from: day0n
PR: hugegraph/hugegraph-ai#16
File: hugegraph-llm/src/hugegraph_llm/config/models/base_prompt_config.py:124-137
Timestamp: 2025-06-25T09:50:06.213Z
Learning: Language-specific prompt attributes (answer_prompt_CN, answer_prompt_EN, extract_graph_prompt_CN, extract_graph_prompt_EN, gremlin_generate_prompt_CN, gremlin_generate_prompt_EN, keywords_extract_prompt_CN, keywords_extract_prompt_EN, doc_input_text_CN, doc_input_text_EN) are defined in the PromptConfig class in hugegraph-llm/src/hugegraph_llm/config/prompt_config.py, which inherits from BasePromptConfig, making these attributes accessible in the parent class methods.
Applied to files:
hugegraph-llm/src/hugegraph_llm/operators/llm_op/prompt_generate.pyhugegraph-llm/src/hugegraph_llm/api/models/rag_requests.pyhugegraph-llm/src/hugegraph_llm/demo/rag_demo/text2gremlin_block.pyhugegraph-llm/src/hugegraph_llm/config/prompt_config.pyhugegraph-llm/src/hugegraph_llm/config/models/base_prompt_config.pyhugegraph-llm/src/hugegraph_llm/demo/rag_demo/vector_graph_block.pyhugegraph-llm/src/hugegraph_llm/operators/llm_op/schema_build.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/src/hugegraph_llm/resources/demo/config_prompt.yaml : Keep prompt configuration in src/hugegraph_llm/resources/demo/config_prompt.yaml
Applied to files:
hugegraph-llm/src/hugegraph_llm/operators/llm_op/prompt_generate.pyhugegraph-llm/src/hugegraph_llm/config/prompt_config.pyhugegraph-llm/src/hugegraph_llm/config/models/base_prompt_config.pyhugegraph-llm/src/hugegraph_llm/operators/llm_op/schema_build.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/src/hugegraph_llm/config/**/*.py : Keep configuration management code under src/hugegraph_llm/config/
Applied to files:
hugegraph-llm/src/hugegraph_llm/demo/rag_demo/configs_block.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/src/hugegraph_llm/models/**/*.py : Implement LLM, embedding, and reranker models under src/hugegraph_llm/models/
Applied to files:
hugegraph-llm/src/hugegraph_llm/models/embeddings/base.pyhugegraph-llm/src/hugegraph_llm/models/llms/base.pyhugegraph-llm/src/hugegraph_llm/models/llms/init_llm.pyhugegraph-llm/src/hugegraph_llm/config/llm_config.py
📚 Learning: 2025-08-29T13:11:08.943Z
Learnt from: Gfreely
PR: hugegraph/hugegraph-ai#32
File: hugegraph-llm/src/hugegraph_llm/operators/llm_op/keyword_extract.py:113-154
Timestamp: 2025-08-29T13:11:08.943Z
Learning: 在 hugegraph-llm 的 KeywordExtract 类中，用户 Gfreely 希望保持提取方法的接口一致性：所有提取方法（_extract_with_llm、_extract_with_textrank、_extract_with_hybrid）都返回 Dict[str, float]，由主 run() 方法统一处理排序和截断，而不是在各个提取方法内部进行预处理。这是他们的架构设计偏好。
Applied to files:
hugegraph-llm/src/hugegraph_llm/operators/document_op/word_extract.pyhugegraph-llm/src/hugegraph_llm/operators/llm_op/keyword_extract.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/**/*.py : Adhere to ruff code style for Python code
Applied to files:
hugegraph-llm/src/hugegraph_llm/utils/hugegraph_utils.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Applies to hugegraph-llm/src/hugegraph_llm/utils/**/*.py : Place utilities, logging, and decorators under src/hugegraph_llm/utils/
Applied to files:
hugegraph-llm/src/hugegraph_llm/utils/hugegraph_utils.py
📚 Learning: 2025-06-25T09:45:10.751Z
Learnt from: day0n
PR: hugegraph/hugegraph-ai#16
File: hugegraph-llm/src/hugegraph_llm/config/models/base_prompt_config.py:100-116
Timestamp: 2025-06-25T09:45:10.751Z
Learning: In hugegraph-llm BasePromptConfig class, llm_settings is a runtime property that is loaded from config through dependency injection during object initialization, not a static class attribute. Static analysis tools may flag this as missing but it's intentional design.
Applied to files:
hugegraph-llm/src/hugegraph_llm/config/prompt_config.pyhugegraph-llm/src/hugegraph_llm/config/llm_config.py
📚 Learning: 2025-05-27T06:55:13.779Z
Learnt from: cgwer
PR: hugegraph/hugegraph-ai#10
File: hugegraph-python-client/pyproject.toml:0-0
Timestamp: 2025-05-27T06:55:13.779Z
Learning: The hugegraph-python-client is a component within the hugegraph-ai project repository (apache/incubator-hugegraph-ai), not a standalone repository. When reviewing project URLs in pyproject.toml files within this project, they should point to the main hugegraph-ai repository.
Applied to files:
hugegraph-python-client/src/tests/client_utils.py
📚 Learning: 2025-08-18T13:20:30.343Z
Learnt from: Gfreely
PR: hugegraph/hugegraph-ai#32
File: hugegraph-llm/src/hugegraph_llm/operators/llm_op/keyword_extract.py:61-63
Timestamp: 2025-08-18T13:20:30.343Z
Learning: In hugegraph-llm KeywordExtract, NLTKHelper loads both English and Chinese stopwords during initialization, but the stopwords(lang) method still requires the correct language key ("english" or "chinese") to return the appropriate stopword set for filtering.
Applied to files:
hugegraph-llm/src/tests/operators/common_op/test_nltk_helper.py
📚 Learning: 2025-08-18T13:20:30.343Z
Learnt from: Gfreely
PR: hugegraph/hugegraph-ai#32
File: hugegraph-llm/src/hugegraph_llm/operators/llm_op/keyword_extract.py:61-63
Timestamp: 2025-08-18T13:20:30.343Z
Learning: NLTKHelper in hugegraph-llm uses lazy loading for stopwords and calls nltk.corpus.stopwords.words(lang) directly with the provided language parameter. It does not preload both English and Chinese stopwords - each language is loaded on first access. The lang parameter must match NLTK's expected language codes ("english", "chinese") or it will fail.
Applied to files:
hugegraph-llm/src/tests/operators/common_op/test_nltk_helper.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Configure LLM providers via LiteLLM and openai/ollama clients
Applied to files:
hugegraph-llm/src/hugegraph_llm/config/llm_config.py
📚 Learning: 2025-09-16T06:40:44.968Z
Learnt from: CR
PR: hugegraph/hugegraph-ai#0
File: hugegraph-llm/AGENTS.md:0-0
Timestamp: 2025-09-16T06:40:44.968Z
Learning: Configure HugeGraph connection via environment variables
Applied to files:
hugegraph-llm/src/hugegraph_llm/config/hugegraph_config.py
🪛 GitHub Actions: Pylint
hugegraph-llm/src/hugegraph_llm/nodes/llm_node/schema_build.py
[error] 18-18: E0611: No name 'CStatus' in module 'PyCGraph' (no-name-in-module)
[warning] 85-85: R1705: Unnecessary "elif" after "return", remove the leading "el" from "elif" (no-else-return)
hugegraph-llm/src/hugegraph_llm/api/admin_api.py
[error] 34-34: E0702: Raising dict while only classes or instances are allowed (raising-bad-type)
hugegraph-llm/src/hugegraph_llm/models/llms/init_llm.py
[warning] 25-25: W0621: Redefining name 'llm_settings' from outer scope (redefined-outer-name)
hugegraph-llm/src/hugegraph_llm/nodes/hugegraph_node/gremlin_execute.py
[error] 20-20: E0611: No name 'CStatus' in module 'PyCGraph' (no-name-in-module)
hugegraph-llm/src/hugegraph_llm/nodes/hugegraph_node/schema.py
[error] 18-18: E0611: No name 'CStatus' in module 'PyCGraph' (no-name-in-module)
hugegraph-llm/src/hugegraph_llm/nodes/llm_node/text2gremlin.py
[error] 21-21: E0611: No name 'CStatus' in module 'PyCGraph' (no-name-in-module)
hugegraph-llm/src/hugegraph_llm/state/ai_state.py
[error] 16-16: E0611: No name 'GParam' in module 'PyCGraph' (no-name-in-module)
[error] 16-16: E0611: No name 'CStatus' in module 'PyCGraph' (no-name-in-module)
🔇 Additional comments (33)
hugegraph-llm/src/hugegraph_llm/api/exceptions/rag_exceptions.py (1)
24-26: 格式调整合理仅做了参数换行，提升了可读性，不影响原有行为。
hugegraph-llm/src/hugegraph_llm/flows/prompt_generate.py (1)
61-61: 返回语句调整合理简化为单行后逻辑保持不变，默认提示信息仍能覆盖缺省场景，看起来没有风险。
hugegraph-llm/src/hugegraph_llm/operators/document_op/word_extract.py (1)
62-62: 引号风格统一无行为影响仅替换了日志调用处的引号样式，功能保持一致。
hugegraph-python-client/src/pyhugegraph/structure/property_key_data.py (1)
65-67: 格式化调整保持原有输出多行 f-string 与之前逻辑一致，
__repr__的语义未变更。hugegraph-llm/src/hugegraph_llm/models/llms/openai.py (2)
45-45: 空字符串默认值一致即可这里的引号风格调整不影响逻辑，维持现状没问题。
189-189: 流式参数补逗号没问题仅是格式化补全尾随逗号，对功能无影响，保持即可。
hugegraph-llm/src/hugegraph_llm/models/llms/init_llm.py (1)
176-177: 格式收敛保持行为不变这一行的单行化调整未改变
generate调用语义，运行效果保持一致。hugegraph-python-client/src/tests/api/test_auth.py (2)
101-101: 格式调整保持语义不变修改为单行调用后可读性更好，逻辑与原实现一致。
136-136: 断言简化正确断言被压缩为单行但仍覆盖同样的校验，语义未变。
hugegraph-llm/src/hugegraph_llm/flows/import_graph_data.py (1)
38-42: 日志截断格式调整合理新增括号仅限缩进与可读性优化，未改变原有逻辑，保持现有行为一致。
hugegraph-llm/src/tests/config/test_config.py (1)
25-27: 保持导入区块整洁在局部导入之间增加空行能提高可读性，这里改动合理。
hugegraph-python-client/src/tests/api/test_version.py (1)
45-48: 字符串引号风格统一将键访问改为双引号让风格与文件其余部分保持一致，改动良好。
hugegraph-llm/src/hugegraph_llm/operators/hugegraph_op/schema_manager.py (1)
39-46: 保持原有行为的格式调整这里将字典推导式压缩到一行，仅为格式化变动，不影响
vertexlabels的筛选逻辑。hugegraph-llm/src/tests/operators/common_op/test_check_schema.py (1)
29-40: 测试数据格式化调整无行为变化将期望数据结构改为单行表示，断言仍验证相同的字典内容，测试语义保持不变。
hugegraph-python-client/src/pyhugegraph/api/auth.py (4)
86-88: 格式调整符合预期Line 87 将函数签名压缩到单行并保留
pylint忽略注释，不影响实际行为，保持一致性即可。
116-118: 格式调整符合预期Line 118 仅对参数声明做单行化处理，未动到方法逻辑，与现有风格保持一致。
128-130: 格式调整符合预期Line 129 与前述改动一致，仅是签名格式变化，调用路径与返回值不受影响。
201-203: 格式调整符合预期Line 202 保持
pylint注释与函数签名同在一行，逻辑保持不变，可继续沿用。hugegraph-llm/src/hugegraph_llm/models/llms/litellm.py (2)
51-55: 尾逗号有助于未来修改在
retry_if_exception_type末尾补上尾逗号能保持参数列表的一致性，并减少后续新增异常类型时的 diff 噪音，赞成保留。
86-88: 异步签名缩进调整
agenerate的参数缩进与常规风格保持一致，可读性更好，没有功能性风险。hugegraph-llm/src/tests/models/llms/test_ollama_client.py (1)
35-37: 格式化调整提升可读性调用语义保持一致，新排版让参数结构更紧凑易读，没有新的风险。
hugegraph-llm/src/hugegraph_llm/models/llms/ollama.py (1)
53-56: 格式调整保持原有含义此次仅压缩了
usage字典的书写形式，仍然从响应中读取相同的 token 字段，未引入行为变化。确认无误。hugegraph-llm/src/hugegraph_llm/utils/graph_index_utils.py (1)
48-61: 保持原有逻辑 👍这一段改动仅调整了
KgBuilder及相关变量的排版，参数顺序与原实现一致，行为不受影响。hugegraph-llm/src/hugegraph_llm/nodes/hugegraph_node/schema.py (1)
65-65: 改用日志输出符合现有模式这里改成
log.debug便于集中管理日志级别，比直接hugegraph-python-client/src/pyhugegraph/example/hugegraph_example.py (2)
29-35: Schema 链式定义更紧凑这段链式调用补齐了
Person的birthDate属性并为ActedIn加上ifNotExist()，既保持了原有的主键语义，也保证了 schema 初始化的幂等性。赞。
48-48: 示例数据风格统一把第三部电影的
addVertex收敛成与前面一致的单行写法，可读性更好，逻辑保持不变。hugegraph-llm/src/hugegraph_llm/operators/common_op/check_schema.py (1)
79-88: 格式化重构符合预期这里将
_process_keys与_add_missing_properties的调用改为单行，仅调整排版；默认参数与校验逻辑保持原值，行为未变化，看起来很好。hugegraph-llm/src/hugegraph_llm/utils/log.py (1)
34-35: 格式化保持一致性即可Line 34 的尾随逗号处理保持了整段参数列表的风格一致，没有引入功能性变化，改动合理。
hugegraph-llm/src/hugegraph_llm/demo/rag_demo/app.py (1)
168-169: 日志语句简化很好Line 168 将
log.info改成单行形式，信息内容未变，代码更简洁清晰，赞同。hugegraph-llm/src/hugegraph_llm/config/prompt_config.py (1)
26-27: 空行让段落更清晰Line 26 之后补了一行空白，使注释与属性段落更好分隔，可读性提升，无副作用。
hugegraph-llm/src/hugegraph_llm/operators/index_op/vector_index_query.py (1)
33-39: 参数换行提升可读性Line 33-39 将
get_index_folder_name和get_filename_prefix的参数按行分隔，可读性更好，同时保持旧逻辑，认可。hugegraph-llm/src/hugegraph_llm/flows/get_graph_index_info.py (1)
51-51: 调用格式统一即可Line 51 调整为单行调用
get_index_folder_name，与其他文件保持风格一致，不影响行为。hugegraph-llm/src/hugegraph_llm/flows/text2gremlin.py (1)
105-105: 注释需使用英文该行仍为中文注释，与仓库统一使用英文的约定（此前 review 已提示）不一致，请改成英文说明以避免风格漂移。
[建议修复如下]- # 始终返回 5 个标准键，避免前端因过滤异常看不到字段 + # Always return 5 standard keys to prevent frontend filters from hiding fields unexpectedly
| raise generate_response( | ||
| RAGResponse( | ||
| status_code=status.HTTP_403_FORBIDDEN, # pylint: disable=E0702 | ||
| message="Invalid admin_token", | ||
| ) | ||
| ) |
There was a problem hiding this comment.
错误地抛出了非异常对象
这里仍然使用 raise generate_response(...) 抛出一个字典/响应对象，触发运行时报错和当前 Pylint 的 E0702 失败。应该直接返回该响应或改为抛出 HTTPException。建议修改为直接 return generate_response(...) 以保持兼容现有返回路径。
- raise generate_response(
- RAGResponse(
- status_code=status.HTTP_403_FORBIDDEN, # pylint: disable=E0702
- message="Invalid admin_token",
- )
- )
+ return generate_response(
+ RAGResponse(
+ status_code=status.HTTP_403_FORBIDDEN,
+ message="Invalid admin_token",
+ )
+ )📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| raise generate_response( | |
| RAGResponse( | |
| status_code=status.HTTP_403_FORBIDDEN, # pylint: disable=E0702 | |
| message="Invalid admin_token", | |
| ) | |
| ) | |
| return generate_response( | |
| RAGResponse( | |
| status_code=status.HTTP_403_FORBIDDEN, | |
| message="Invalid admin_token", | |
| ) | |
| ) |
🧰 Tools
🪛 GitHub Actions: Pylint
[error] 34-34: E0702: Raising dict while only classes or instances are allowed (raising-bad-type)
🤖 Prompt for AI Agents
In hugegraph-llm/src/hugegraph_llm/api/admin_api.py around lines 34 to 39, the
code incorrectly uses "raise generate_response(...)" which raises a
non-exception object and triggers runtime/Pylint E0702; change this to directly
"return generate_response(...)" to match the existing response flow, or
alternatively raise a proper HTTPException with the same status_code and message
if you intend to throw — ensure the chosen approach is applied consistently with
surrounding handlers.
| extract_template=keywords_extract_prompt | ||
| ).keywords_to_vid().import_schema(huge_settings.graph_name).query_graphdb( | ||
| num_gremlin_generate_example=gremlin_tmpl_num, | ||
| gremlin_prompt=gremlin_prompt, | ||
| ) |
There was a problem hiding this comment.
恢复 streaming 流程的关键词召回筛选参数
这里把 keywords_to_vid 的 vector_dis_threshold 和 topk_per_keyword 参数直接移除了，导致流式回答路径不再应用与非流式路径相同的向量距离阈值和 TopK 筛选逻辑。现有 UI/后端配置里的这些阈值会被忽略，召回范围变宽，结果与非流式接口不一致，实际效果明显退化。请恢复这些参数的传入，保持两条路径的行为一致。
- rag.extract_keywords(
- extract_template=keywords_extract_prompt
- ).keywords_to_vid().import_schema(huge_settings.graph_name).query_graphdb(
+ rag.extract_keywords(
+ extract_template=keywords_extract_prompt
+ ).keywords_to_vid(
+ vector_dis_threshold=vector_dis_threshold,
+ topk_per_keyword=topk_per_keyword,
+ ).import_schema(huge_settings.graph_name).query_graphdb(📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| extract_template=keywords_extract_prompt | |
| ).keywords_to_vid().import_schema(huge_settings.graph_name).query_graphdb( | |
| num_gremlin_generate_example=gremlin_tmpl_num, | |
| gremlin_prompt=gremlin_prompt, | |
| ) | |
| rag.extract_keywords( | |
| extract_template=keywords_extract_prompt | |
| ).keywords_to_vid( | |
| vector_dis_threshold=vector_dis_threshold, | |
| topk_per_keyword=topk_per_keyword, | |
| ).import_schema(huge_settings.graph_name).query_graphdb( | |
| num_gremlin_generate_example=gremlin_tmpl_num, | |
| gremlin_prompt=gremlin_prompt, | |
| ) |
| from PyCGraph import CStatus | ||
|
|
||
| from hugegraph_llm.nodes.base_node import BaseNode | ||
| from hugegraph_llm.operators.llm_op.gremlin_generate import GremlinGenerateSynthesize | ||
| from hugegraph_llm.models.llms.init_llm import LLMs | ||
| from hugegraph_llm.config import prompt as prompt_cfg | ||
|
|
||
|
|
||
| def _stable_schema_string(state_json: Dict[str, Any]) -> str: | ||
| if "simple_schema" in state_json and state_json["simple_schema"] is not None: | ||
| return json.dumps(state_json["simple_schema"], ensure_ascii=False, sort_keys=True) | ||
| if "schema" in state_json and state_json["schema"] is not None: | ||
| return json.dumps(state_json["schema"], ensure_ascii=False, sort_keys=True) | ||
| return "" | ||
|
|
||
|
|
||
| class Text2GremlinNode(BaseNode): | ||
| operator: GremlinGenerateSynthesize | ||
|
|
||
| def node_init(self): | ||
| # Select LLM | ||
| llm = LLMs().get_text2gql_llm() | ||
| # Serialize schema deterministically | ||
| state_json = self.context.to_json() | ||
| schema_str = _stable_schema_string(state_json) | ||
| # Prompt fallback | ||
| gremlin_prompt: Optional[str] = getattr(self.wk_input, "gremlin_prompt", None) | ||
| if gremlin_prompt is None or not str(gremlin_prompt).strip(): | ||
| gremlin_prompt = prompt_cfg.gremlin_generate_prompt | ||
| # Keep vertices/properties empty for now | ||
| self.operator = GremlinGenerateSynthesize( | ||
| llm=llm, | ||
| schema=schema_str, | ||
| vertices=None, | ||
| gremlin_prompt=gremlin_prompt, | ||
| ) | ||
| return CStatus() |
There was a problem hiding this comment.
修复 PyCGraph 状态导入以通过构建
PyCGraph 模块当前并没有导出 CStatus，GitHub Actions 的 pylint 也因此报错（E0611: no-name-in-module）。如果不修正，这个节点在加载阶段就会抛 ImportError，整条 Text2Gremlin 流程无法初始化。请按照 PCGraph SDK 实际提供的状态类来调整——例如改成 SDK 文档中的 Status/StatusCode 并返回 Status.ok()（或对应的成功状态）——以确保 node_init 返回有效的状态对象并让流水线恢复通过。
🧰 Tools
🪛 GitHub Actions: Pylint
[error] 21-21: E0611: No name 'CStatus' in module 'PyCGraph' (no-name-in-module)
🤖 Prompt for AI Agents
In hugegraph-llm/src/hugegraph_llm/nodes/llm_node/text2gremlin.py around lines
21 to 57, the code imports CStatus from PyCGraph which is not exported; update
the import to use the actual status type provided by the PCGraph SDK (e.g.,
import Status or Status/StatusCode per SDK docs), replace the return CStatus()
with the SDK's success value (for example return Status.ok() or equivalent
success constructor), and ensure any required StatusCode usage is adjusted so
node_init returns a valid status object accepted by the pipeline.
| context_str = ( | ||
| f"{context_head_str}\n" f"{self._context_body}\n" f"{context_tail_str}".strip("\n") | ||
| ) |
There was a problem hiding this comment.
修正 .strip() 作用范围导致的格式回归
这里把 .strip("\n") 只作用在最后一个 f-string 上，无法再去掉前两段拼接时引入的首尾换行，context_head_str 或 context_tail_str 为空时会产生额外空行，行为与之前版本不同。请恢复为对整个拼接后的字符串调用 .strip()；run_streaming、async_generate、async_streaming_generate 中的相同拼接也需要同步调整。
- context_str = (
- f"{context_head_str}\n" f"{self._context_body}\n" f"{context_tail_str}".strip("\n")
- )
+ context_str = (
+ f"{context_head_str}\n"
+ f"{self._context_body}\n"
+ f"{context_tail_str}"
+ ).strip("\n")📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| context_str = ( | |
| f"{context_head_str}\n" f"{self._context_body}\n" f"{context_tail_str}".strip("\n") | |
| ) | |
| context_str = ( | |
| f"{context_head_str}\n" | |
| f"{self._context_body}\n" | |
| f"{context_tail_str}" | |
| ).strip("\n") |
| url=self.URL, | ||
| user=self.USERNAME, | ||
| pwd=self.PASSWORD, | ||
| graph=self.GRAPH, | ||
| graphspace=self.GRAPHSPACE, | ||
| ) |
There was a problem hiding this comment.
Restore timeout argument
这里移除了 timeout 参数，PyHugeClient 现在会退回到内部默认的 (0.5, 15.0)。我们此前在 ClientUtils.TIMEOUT 中专门维护了 10 秒的容忍度，就是为了避免本地/CI 环境下连接风波导致的拒连；现在这个常量被闲置（也意味着行为回退），很容易重现间歇性失败。建议继续显式传入超时，并且同时满足 tuple[float, float] 的类型约束。可以这样调整：
self.client = PyHugeClient(
url=self.URL,
user=self.USERNAME,
pwd=self.PASSWORD,
graph=self.GRAPH,
graphspace=self.GRAPHSPACE,
+ timeout=(self.TIMEOUT, self.TIMEOUT),
)📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| url=self.URL, | |
| user=self.USERNAME, | |
| pwd=self.PASSWORD, | |
| graph=self.GRAPH, | |
| graphspace=self.GRAPHSPACE, | |
| ) | |
| self.client = PyHugeClient( | |
| url=self.URL, | |
| user=self.USERNAME, | |
| pwd=self.PASSWORD, | |
| graph=self.GRAPH, | |
| graphspace=self.GRAPHSPACE, | |
| timeout=(self.TIMEOUT, self.TIMEOUT), | |
| ) |
🤖 Prompt for AI Agents
In hugegraph-python-client/src/tests/client_utils.py around lines 31 to 36, the
call creating PyHugeClient removed the timeout argument causing the client to
fall back to its internal (0.5, 15.0) timeout; restore explicit timeout by
passing ClientUtils.TIMEOUT (or convert it to a tuple[float, float] if needed)
into the PyHugeClient constructor so tests use the intended 10s tolerance and
avoid intermittent connection failures.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Linyu <94553312+weijinglin@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Linyu <94553312+weijinglin@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Linyu <94553312+weijinglin@users.noreply.github.com>
2 participants
Summary by CodeRabbit
新功能
改进
样式/杂项