Home / OpenBMB / UltraRAG
Repository Analysis

OpenBMB/UltraRAG

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

10.5 Low AI signal View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of OpenBMB/UltraRAG, a Python project with 5,675 GitHub stars. SynthScan v2.0 examined 67,340 lines of code across 208 source files, recording 502 pattern matches distributed across 14 syntactic categories. The overall adjusted score of 10.5 places this repository in the Low AI signal band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

10.5
Adjusted Score
10.5
Raw Score
100%
Time Factor
2026-08-02
Last Push
5.7K
Stars
Python
Language
67.3K
Lines of Code
208
Files
502
Pattern Hits
2026-08-02
Scan Date
0.25
HC Hit Rate

What These Metrics Mean

Adjusted Score
Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score
The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor
The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits
Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate
High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files
Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 53MEDIUM 39LOW 410

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 502 distinct pattern matches across 14 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Docstring Block Structure35 hits · 175 pts
SeverityFileLineSnippetContext
HIGHui/backend/pipeline_manager.py611Execute multi-turn conversation generation. Args: callback: Stream callback function dySTRING
HIGHui/backend/pipeline_manager.py661Run chat pipeline execution. Args: callback: Stream callback function dynamic_params: OSTRING
HIGHui/backend/pipeline_manager.py2271Parse arbitrary YAML text and return safe Python object. Args: yaml_content: YAML content string ReturSTRING
HIGHui/backend/pipeline_manager.py2327Save YAML text content directly to file. Args: name: Pipeline name yaml_content: YAML content strinSTRING
HIGHui/backend/pipeline_manager.py2363Rename a pipeline file. Args: old_name: Current pipeline name new_name: New pipeline name RetuSTRING
HIGHui/backend/pipeline_manager.py3164Upload multiple files to knowledge base. Args: file_objs: List of file objects to upload Returns: STRING
HIGHui/backend/pipeline_manager.py3239Delete a knowledge base file or collection. Args: category: File category (raw, corpus, chunks, collection,STRING
HIGHui/backend/pipeline_manager.py3290Delete a Milvus collection. Args: name: Collection name Returns: Dictionary with deletion statSTRING
HIGHui/backend/pipeline_manager.py3382Run knowledge base pipeline tool. Args: pipeline_name: Name of the pipeline to run target_file_pathSTRING
HIGHservers/benchmark/src/benchmark.py19Load data from file in various formats (jsonl, json, parquet). Args: path: Path to the data file liSTRING
HIGHservers/benchmark/src/benchmark.py114Load benchmark data from file with key mapping and optional shuffling. Args: benchmark: Dictionary containiSTRING
HIGHservers/reranker/src/reranker.py158Rerank passages for queries using the initialized reranker backend. Args: query_list: List of querySTRING
HIGHservers/corpus/src/corpus.py23Validate and sanitize file path to prevent path traversal attacks. Args: user_path: User-provided file STRING
HIGHservers/retriever/src/retriever.py870Search for passages using query embeddings. Args: query_list: List of query strings topSTRING
HIGHservers/retriever/src/retriever.py1064Search using remote retriever deployment. Args: retriever_url: URL of remote retriever service STRING
HIGHservers/retriever/src/index_backends/faiss_backend.py180Search for similar passages using FAISS index. Args: query_embeddings: 2D numpy array of query embeSTRING
HIGHservers/retriever/src/index_backends/milvus_backend.py86Resolve Milvus URI from config. Args: index_path: URI string from config Returns: STRING
HIGHservers/retriever/src/index_backends/milvus_backend.py314Search for similar passages using Milvus index. Args: query_embeddings: 2D numpy array of query embSTRING
HIGHservers/prompt/src/prompt.py21Validate template path to prevent path traversal. Args: template_path: Path to template file STRING
HIGHservers/prompt/src/prompt.py48Load Jinja2 template from file with security validation. Args: template_path: Path to template file ReSTRING
HIGHservers/evaluation/src/evaluation.py371Evaluate retrieval results using pytrec_eval. Args: qrels_path: Path to TREC qrels file run_path: PSTRING
HIGHservers/evaluation/src/evaluation.py428Save evaluation results to JSON file and optionally display as Markdown table. Args: results: Dictionary ofSTRING
HIGHservers/generation/src/generation.py86Extract text content from various prompt formats. Args: prompt_ls: List of prompts in various formaSTRING
HIGHservers/generation/src/generation.py125Convert image path to data URL. Args: path_or_url: Image file path or URL Returns: STRING
HIGHservers/generation/src/generation.py289Internal method to generate responses from message lists. Args: msg_ls: List of message lists (one STRING
HIGHservers/generation/src/generation.py513Generate responses with multimodal inputs (text + images). Args: multimodal_path: List of image patSTRING
HIGHservers/generation/src/local_generation.py46Extract text content from various prompt formats. Args: prompt_ls: List of prompts in various formaSTRING
HIGHservers/generation/src/local_generation.py81Convert image path to data URL. Args: path_or_url: Image file path or URL Returns: STRING
HIGHservers/router/src/router.py25Route queries to state1 or state2 based on query value. Args: query_list: List of query strings ReturnSTRING
HIGHsrc/ultrarag/server.py330Register a prompt with UltraRAG-specific output annotation support. Args: name_or_fn: Prompt name oSTRING
HIGHsrc/ultrarag/server.py480Build a tool/prompt entry for server.yaml. Args: meta: Metadata dictionary containing function infoSTRING
HIGHsrc/ultrarag/client.py391Pad sub-list to match skeleton structure. Args: skeleton: Skeleton list structure parenSTRING
HIGHsrc/ultrarag/client.py606Get input data for a tool execution step. Args: server_name: Name of the server tool_naSTRING
HIGHsrc/ultrarag/client.py1189Load pipeline context from configuration files. Args: config_path: Path to pipeline configuration file STRING
HIGHsrc/ultrarag/api.py151Get a proxy for the specified server. Args: server: Name of the server to access Returns: STRING
Excessive Try-Catch Wrapping174 hits · 129 pts
SeverityFileLineSnippetContext
LOWui/backend/kb_visibility_store.py412 except Exception:STRING
LOWui/backend/chat_store.py353 except Exception:STRING
LOWui/backend/chat_store.py372 except Exception:STRING
LOW⚡ui/backend/app.py98 except Exception as e:CODE
LOW⚡ui/backend/app.py535 except Exception as exc:CODE
LOW⚡ui/backend/app.py541 except Exception as exc:CODE
LOWui/backend/app.py308 except Exception as e:CODE
LOWui/backend/app.py418 except Exception as e:CODE
LOWui/backend/app.py455 except Exception as e:CODE
LOWui/backend/app.py914 except Exception as e:CODE
LOWui/backend/app.py934 except Exception as e:CODE
LOWui/backend/app.py953 except Exception as e:CODE
LOWui/backend/app.py984 except Exception as e:CODE
LOWui/backend/app.py1003 except Exception as e:CODE
LOWui/backend/app.py1016 except Exception as e:CODE
LOWui/backend/app.py1044 except Exception as e:CODE
LOWui/backend/app.py1067 except Exception as e:CODE
LOWui/backend/app.py1113 except Exception:CODE
LOWui/backend/app.py1393 except Exception as e:CODE
LOWui/backend/app.py1424 except Exception as e:CODE
LOWui/backend/app.py1479 except Exception as e:CODE
LOWui/backend/app.py1620 except Exception as e:CODE
LOWui/backend/app.py1711 except Exception as e:CODE
LOWui/backend/app.py1728 except Exception as e:CODE
LOWui/backend/app.py1825 except Exception as e:CODE
LOWui/backend/app.py1924 except Exception as exc:CODE
LOWui/backend/app.py1987 except Exception as e:CODE
LOWui/backend/app.py2029 except Exception as exc:CODE
LOWui/backend/app.py2034 except Exception as e:CODE
LOWui/backend/app.py2047 except Exception as e:CODE
LOWui/backend/app.py2108 except Exception as e:CODE
LOWui/backend/app.py2458 except Exception as e:CODE
LOWui/backend/app.py2475 except Exception:CODE
LOWui/backend/app.py2478 except Exception:CODE
LOWui/backend/app.py2554 except Exception:CODE
LOWui/backend/app.py2570 except Exception as e:CODE
LOWui/backend/app.py2681 except Exception as e:CODE
LOWui/backend/app.py2771 except Exception:CODE
LOWui/backend/app.py2822 except Exception:CODE
MEDIUMui/backend/pipeline_manager.py50def _safe_stdio_del(self):CODE
MEDIUMui/backend/pipeline_manager.py1072def run_bg():CODE
MEDIUMui/backend/pipeline_manager.py1919def _run() -> None:CODE
LOW⚡ui/backend/pipeline_manager.py1492 except Exception:CODE
LOW⚡ui/backend/pipeline_manager.py1846 except Exception:CODE
LOW⚡ui/backend/pipeline_manager.py1911 except Exception as exc:CODE
LOW⚡ui/backend/pipeline_manager.py1923 except Exception as exc:CODE
LOW⚡ui/backend/pipeline_manager.py3491 except Exception:CODE
LOW⚡ui/backend/pipeline_manager.py3496 except Exception as exc:CODE
LOW⚡ui/backend/pipeline_manager.py3502 except Exception:CODE
LOWui/backend/pipeline_manager.py59 except Exception as exc: # pragma: no cover - best effort guardCODE
LOWui/backend/pipeline_manager.py64except Exception as exc: # pragma: no cover - defensiveCODE
LOWui/backend/pipeline_manager.py89 except Exception as exc:CODE
LOWui/backend/pipeline_manager.py93except Exception as exc: # pragma: no cover - defensiveCODE
LOWui/backend/pipeline_manager.py195 except Exception:CODE
LOWui/backend/pipeline_manager.py254 except Exception:CODE
LOWui/backend/pipeline_manager.py334 except Exception:CODE
LOWui/backend/pipeline_manager.py417 except Exception as e:CODE
LOWui/backend/pipeline_manager.py428 except Exception as e:CODE
LOWui/backend/pipeline_manager.py437 except Exception as e:CODE
LOWui/backend/pipeline_manager.py522 except Exception as e:CODE
114 more matches not shown…
Cross-Language Confusion15 hits · 95 pts
SeverityFileLineSnippetContext
HIGH⚡script/case_study.py324let lightboxEl = null;CODE
HIGH⚡script/case_study.py325let lightboxImgEl = null;CODE
HIGH⚡script/case_study.py326let lightboxCloseBtn = null;CODE
HIGH⚡script/case_study.py479 (function w(x){ if(x==null)return; if(Array.isArray(x)){x.forEach(w);}CODE
HIGH⚡script/case_study.py481 else if(typeof x==="string"&&isImagePath(x)){out.push(x);} })(v);CODE
HIGH⚡script/case_study.py486 (function w(x){ if(!ok)return; if(x==null)return; if(Array.isArray(x)){x.forEach(w);}CODE
HIGH⚡script/case_study.py495 var stepName = String((st && st.step) != null ? st.step : "unknown");CODE
HIGH⚡script/case_study.py496 var memory = (st && st.memory) != null ? st.memory : {};CODE
HIGHscript/case_study.py377 openLightbox(img.dataset.fullSrc || img.src, altLabel || img.alt || "");CODE
HIGHscript/case_study.py436 history.replaceState(null, "", `#case-${state.idx}`);CODE
HIGHscript/case_study.py462 var names = steps.map(function(s){ return (s && s.step) ? s.step : "unknown"; });CODE
HIGHscript/case_study.py532 } else if (imagesOnly && imgs.length > 0) {CODE
HIGHscript/case_study.py548 else { try { pt = JSON.stringify(val, null, 2); } catch(e) { pt = String(val); } }CODE
HIGHscript/case_study.py583 var allOpen = bodies.length > 0 && bodies.every(function(c){ return c.classList.contains("open"); });CODE
HIGHscript/case_study.py612 history.replaceState(null, "", `#case-${state.idx}`);CODE
Hyper-Verbose Identifiers91 hits · 80 pts
SeverityFileLineSnippetContext
LOWui/frontend/src/shared/lib/pipelinePreview.ts424export function serializePipelinePreviewToYaml(nodes: PipelinePreviewNode[]): string {CODE
LOWui/frontend/src/shared/api/pipelines.ts46export async function stopPipelineChatGeneration(sessionId: string): Promise<unknown> {CODE
LOWui/frontend/src/shared/api/pipelines.ts67export async function startPipelineBackgroundChat(CODE
LOWui/frontend/src/shared/api/backgroundTasks.ts33export async function clearCompletedBackgroundTasks(): Promise<{ status: string; count: number }> {CODE
LOW⚡ui/frontend/src/pages/ChatPage.tsx255function getCurrentUserMemoryCollectionNameSet(rawUserId: string): Set<string> {CODE
LOW⚡ui/frontend/src/pages/ChatPage.tsx260function filterCurrentUserMemoryCollections(CODE
LOW⚡ui/frontend/src/pages/ChatPage.tsx270function isInternalMemoryCollection(name: string): boolean {CODE
LOW⚡ui/frontend/src/pages/ChatPage.tsx276function filterVisibleKbCollections(collections: KbFileEntry[]): KbFileEntry[] {CODE
LOWui/backend/auth.py328 def _ensure_users_table_columns(self, conn: sqlite3.Connection) -> None:CODE
LOWui/backend/auth.py339 def _ensure_default_admin_user(self, conn: sqlite3.Connection) -> None:CODE
LOWui/backend/kb_visibility_store.py50 def normalize_collection_name(self, raw_name: Any) -> str:STRING
LOWui/backend/kb_visibility_store.py275 def filter_viewable_collections(STRING
LOW⚡ui/backend/app.py105def _normalize_memory_user_id(raw_user_id: Optional[str]) -> str:CODE
LOW⚡ui/backend/app.py112def _is_internal_memory_collection_name(raw_name: Any) -> bool:CODE
LOW⚡ui/backend/app.py119def _current_user_memory_collection_names(user_id: str) -> Set[str]:CODE
LOW⚡ui/backend/app.py550 def _filter_collections_by_acl(CODE
LOWui/backend/app.py142def _sanitize_export_filename(title: str) -> str:CODE
LOWui/backend/app.py161def _build_content_disposition(filename: str) -> str:CODE
LOWui/backend/app.py424def _run_memory_sync_background(CODE
LOWui/backend/app.py503 def _get_authenticated_user_id() -> Optional[str]:CODE
LOWui/backend/app.py516 def _ensure_legacy_collection_visibility(collection_names: List[str]) -> None:CODE
LOWui/backend/app.py618 def _build_effective_model_settings(raw_settings: Any) -> Dict[str, Dict[str, str]]:CODE
LOWui/backend/app.py635 def _get_authenticated_user_model_settings() -> Dict[str, Dict[str, str]]:CODE
LOWui/backend/app.py863 def auth_update_model_settings() -> Response:CODE
LOWui/backend/app.py1314 def _normalize_chat_history_for_store(raw_messages: Any) -> list[dict[str, Any]]:CODE
LOWui/backend/app.py1402 def _stream_with_chat_persistence(base_stream):CODE
LOW⚡ui/backend/pipeline_manager.py1479def get_memory_collection_name(user_id: Optional[str]) -> str:CODE
LOW⚡ui/backend/pipeline_manager.py1487def pipeline_uses_memory_retrieval(pipeline_name: Optional[str]) -> bool:CODE
LOW⚡ui/backend/pipeline_manager.py1841def _get_collection_row_count(client: Any, collection_name: str) -> int:CODE
LOW⚡ui/backend/pipeline_manager.py1850def clear_user_memory_collection_vectors(user_id: Optional[str]) -> Dict[str, Any]:CODE
LOW⚡ui/backend/pipeline_manager.py1916def _trigger_memory_sync_async(user_id: str) -> None:CODE
LOW⚡ui/backend/pipeline_manager.py1929def _resolve_memory_server_alias_from_session(CODE
LOWui/backend/pipeline_manager.py147def _normalize_collection_name(raw_name: str) -> str:CODE
LOWui/backend/pipeline_manager.py162def _make_safe_collection_name(display_name: str) -> tuple[str, str]:CODE
LOWui/backend/pipeline_manager.py232def _extract_display_name_from_desc(desc: str, fallback: str) -> str:CODE
LOWui/backend/pipeline_manager.py309def _is_generation_server_path(server_path: str) -> bool:CODE
LOWui/backend/pipeline_manager.py314def _is_retriever_server_path(server_path: str) -> bool:CODE
LOWui/backend/pipeline_manager.py329def _resolve_generation_server_alias(pipeline_name: Optional[str]) -> str:CODE
LOWui/backend/pipeline_manager.py347def _extract_non_empty_model_settings(raw_settings: Any) -> Dict[str, Dict[str, str]]:CODE
LOWui/backend/pipeline_manager.py528 def _build_demo_backend_overrides(CODE
LOWui/backend/pipeline_manager.py1579def _list_project_memory_files(user_id: str) -> List[Path]:CODE
LOWui/backend/pipeline_manager.py1589def _snapshot_project_memory_files(user_id: str, files: List[Path]) -> Dict[str, Any]:CODE
LOWui/backend/pipeline_manager.py1607def _parse_project_memory_turn_chunks(CODE
LOWui/backend/pipeline_manager.py1952def _resolve_memory_server_alias(pipeline_name: Optional[str]) -> Optional[str]:CODE
LOWui/backend/pipeline_manager.py2005def resolve_memory_collection_for_pipeline(CODE
LOWui/backend/pipeline_manager.py2023def trigger_memory_sync_for_pipeline(CODE
LOWui/backend/pipeline_manager.py2037def _normalize_memory_user_id(user_id: Optional[str]) -> str:CODE
LOWui/backend/pipeline_manager.py2071def _auto_save_memory_chat_turn(CODE
LOWui/backend/pipeline_manager.py2270def parse_pipeline_yaml_content(yaml_content: str) -> Dict:CODE
LOWui/backend/pipeline_manager.py2860def clear_completed_background_tasks(user_id: str = "") -> int:CODE
LOWui/backend/pipeline_manager.py3289def _delete_milvus_collection(name: str) -> Dict[str, str]:CODE
LOWdocs/llms.txt529def output_extract_from_boxed(ans_ls: List[str]) -> Dict[str, List[str]]CODE
LOWdocs/llms.txt543def evisrag_output_extract_from_special(ans_ls: List[str]) -> Dict[str, List[str]]CODE
LOWdocs/llms.txt567def surveycpm_parse_search_response(response_ls: List[str], surveycpm_hard_mode: bool = True) -> Dict[str, List]CODE
LOWdocs/llms.txt574def surveycpm_process_passages(ret_psg_ls: List[List[List[str]]]) -> Dict[str, List[str]]CODE
LOWdocs/llms.txt993def qa_rag_boxed_multiple_choice(CODE
LOWdocs/llms.txt1769async def retriever_batch_websearch(CODE
LOWdocs/llms.txt5487def output_extract_from_boxed(ans_ls: List[str]) -> Dict[str, List[str]]:CODE
LOWscript/case_study.py109def _estimate_case_count_from_steps(steps: List[dict]) -> int:CODE
LOWservers/memory/src/memory.py41def _ensure_user_memory_paths(user_id: str) -> tuple[Path, Path]:CODE
31 more matches not shown…
Deep Nesting90 hits · 60 pts
SeverityFileLineSnippetContext
LOWui/backend/app.py461CODE
LOWui/backend/app.py1267CODE
LOWui/backend/app.py2353CODE
LOWui/backend/app.py2462CODE
LOWui/backend/app.py1402CODE
LOWui/backend/pipeline_manager.py1044CODE
LOWui/backend/pipeline_manager.py1156CODE
LOWui/backend/pipeline_manager.py1380CODE
LOWui/backend/pipeline_manager.py1445CODE
LOWui/backend/pipeline_manager.py1487CODE
LOWui/backend/pipeline_manager.py1672CODE
LOWui/backend/pipeline_manager.py1850CODE
LOWui/backend/pipeline_manager.py1973CODE
LOWui/backend/pipeline_manager.py2293CODE
LOWui/backend/pipeline_manager.py2458CODE
LOWui/backend/pipeline_manager.py2937CODE
LOWui/backend/pipeline_manager.py3238CODE
LOWui/backend/pipeline_manager.py3313CODE
LOWui/backend/pipeline_manager.py3370CODE
LOWui/backend/pipeline_manager.py1198CODE
LOWui/backend/pipeline_manager.py1521CODE
LOWui/backend/pipeline_manager.py2301CODE
LOWui/backend/pipeline_manager.py2944CODE
LOWui/backend/pipeline_manager.py3580CODE
LOWui/backend/pipeline_manager.py2536CODE
LOWui/backend/pipeline_manager.py3594CODE
LOWscript/case_study.py29CODE
LOWscript/case_study.py109CODE
LOWscript/case_study.py120CODE
LOWservers/benchmark/src/benchmark.py15CODE
LOWservers/reranker/src/reranker.py36CODE
LOWservers/reranker/src/reranker.py151CODE
LOWservers/corpus/src/corpus.py131CODE
LOWservers/corpus/src/corpus.py169CODE
LOWservers/corpus/src/corpus.py364CODE
LOWservers/corpus/src/corpus.py515CODE
LOWservers/corpus/src/corpus.py674CODE
LOWservers/corpus/src/corpus.py849CODE
LOWservers/corpus/src/corpus.py971CODE
LOWservers/corpus/src/corpus.py399CODE
LOWservers/retriever/src/retriever.py82CODE
LOWservers/retriever/src/retriever.py186CODE
LOWservers/retriever/src/retriever.py505CODE
LOWservers/retriever/src/retriever.py685CODE
LOWservers/retriever/src/retriever.py863CODE
LOWservers/retriever/src/retriever.py128CODE
LOWservers/retriever/src/index_backends/milvus_backend.py217CODE
LOW…rs/retriever/src/websearch_backends/zhipuai_backend.py38CODE
LOW…rs/retriever/src/websearch_backends/zhipuai_backend.py68CODE
LOWservers/prompt/src/prompt.py294CODE
LOWservers/prompt/src/prompt.py732CODE
LOWservers/prompt/src/prompt.py797CODE
LOWservers/prompt/src/prompt.py826CODE
LOWservers/prompt/src/prompt.py862CODE
LOWservers/prompt/src/prompt.py908CODE
LOWservers/evaluation/src/evaluation.py365CODE
LOWservers/evaluation/src/evaluation.py423CODE
LOWservers/evaluation/src/evaluation.py502CODE
LOWservers/evaluation/src/evaluation.py559CODE
LOWservers/evaluation/src/evaluation.py583CODE
30 more matches not shown…
Modern AI Meta-Vocabulary17 hits · 50 pts
SeverityFileLineSnippetContext
MEDIUMAGENTS.md30│ ├── client.py # CLI + pipeline engine + run/build orchestrationCODE
MEDIUMdocs/llms.txt2642# RAG Demo for UltraRAG UICOMMENT
MEDIUMdocs/llms.txt3276# Vanilla RAG with Corpus Indexing DemoCOMMENT
MEDIUMdocs/llms.txt3792## What is RAG?COMMENT
MEDIUMdocs/llms.txt3928## Build RAG PipelineCOMMENT
MEDIUMdocs/llms.txt3951### Write RAG PipelineCOMMENT
MEDIUMexamples/experiments/rag_deploy.yaml1# RAG Deploy DemoCOMMENT
MEDIUMexamples/experiments/rag_loop.yaml1# RAG Loop DemoCOMMENT
MEDIUMexamples/experiments/rag_branch.yaml1# RAG Branch DemoCOMMENT
MEDIUMexamples/experiments/rag_multiple_choice.yaml1# Vanilla RAG Demo for Multiple Choice DatasetsCOMMENT
MEDIUMexamples/experiments/rag_wow.yaml1# Vanilla RAG Demo for WoW DatasetCOMMENT
MEDIUMexamples/experiments/vanilla_rag.yaml1# Vanilla RAG DemoCOMMENT
MEDIUMexamples/experiments/rag_full.yaml1# Vanilla RAG with Corpus Indexing DemoCOMMENT
MEDIUMexamples/experiments/multimodal_rag.yaml1# Multi-Modal RAG DemoCOMMENT
MEDIUMexamples/demos/RAG_memory.yaml1# RAG Memory Demo for UltraRAG UICOMMENT
MEDIUMexamples/demos/RAG_web.yaml1# RAG Demo for UltraRAG UICOMMENT
MEDIUMexamples/demos/RAG.yaml1# RAG Demo for UltraRAG UICOMMENT
Decorative Section Separators16 hits · 29 pts
SeverityFileLineSnippetContext
MEDIUMui/backend/app.py2221 # =========================================COMMENT
MEDIUMui/backend/app.py2223 # =========================================COMMENT
MEDIUMui/backend/app.py2348 # =========================================COMMENT
MEDIUMui/backend/app.py2350 # =========================================COMMENT
MEDIUMsrc/ultrarag/cli.py14# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━COMMENT
MEDIUMsrc/ultrarag/cli.py16# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━COMMENT
MEDIUMsrc/ultrarag/cli.py56# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
MEDIUMsrc/ultrarag/cli.py58# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
MEDIUMsrc/ultrarag/cli.py152# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
MEDIUMsrc/ultrarag/cli.py154# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
MEDIUMsrc/ultrarag/cli.py353# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
MEDIUMsrc/ultrarag/cli.py355# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
MEDIUMsrc/ultrarag/cli.py413# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
MEDIUMsrc/ultrarag/cli.py415# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
MEDIUM⚡src/ultrarag/cli.py520# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
MEDIUM⚡src/ultrarag/cli.py522# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━STRING
Structural Annotation Overuse17 hits · 26 pts
SeverityFileLineSnippetContext
LOW⚡docs/llms.txt3087## Step 1: Compile PipelineCOMMENT
LOW⚡docs/llms.txt3095## Step 2: RunCOMMENT
LOW⚡docs/llms.txt3103## Step 3: Create New Parameter FileCOMMENT
LOWdocs/llms.txt3040## Step 1: Compile and Configure ParametersCOMMENT
LOWdocs/llms.txt3044## Step 2: Create Debug Configuration FileCOMMENT
LOWdocs/llms.txt3069## Step 3: Start DebuggingCOMMENT
LOWdocs/llms.txt3269## Step 1: Write Pipeline Configuration FileCOMMENT
LOWdocs/llms.txt3306## Step 2: Compile Pipeline and Adjust ParametersCOMMENT
LOWdocs/llms.txt3443## Step 3: Run PipelineCOMMENT
LOWdocs/llms.txt3457## Step 4: Visual Analysis Case StudyCOMMENT
LOWdocs/llms.txt4973### Step 1: Configure Alias ServerCOMMENT
LOWdocs/llms.txt5004### Step 2: Call Separately in PipelineCOMMENT
LOWdocs/llms.txt6202### Step 1: Create Server FileCOMMENT
LOWdocs/llms.txt6218### Step 2: Implement Tool FunctionsCOMMENT
LOWdocs/llms.txt6242### Step 3: Configure Parameter FileCOMMENT
LOWdocs/llms.txt6306### Step 1: Prepare Prompt TemplateCOMMENT
LOWdocs/llms.txt6321### Step 2: Implement Tool in Prompt ServerCOMMENT
Unused Imports27 hits · 26 pts
SeverityFileLineSnippetContext
LOWui/backend/auth.py1CODE
LOWui/backend/kb_visibility_store.py1CODE
LOWui/backend/chat_store.py1CODE
LOWui/backend/storage_paths.py1CODE
LOWui/backend/app.py1CODE
LOWui/backend/pipeline_manager.py1CODE
LOWservers/memory/src/memory.py1CODE
LOWservers/memory/src/memory.py7CODE
LOWservers/retriever/src/bm25_tokenizer.py1CODE
LOWservers/retriever/src/index_backends/faiss_backend.py1CODE
LOWservers/retriever/src/index_backends/__init__.py1CODE
LOWservers/retriever/src/index_backends/base.py1CODE
LOWservers/retriever/src/index_backends/milvus_backend.py1CODE
LOWservers/retriever/src/index_backends/milvus_backend.py5CODE
LOW…rs/retriever/src/websearch_backends/zhipuai_backend.py1CODE
LOWservers/retriever/src/websearch_backends/__init__.py1CODE
LOWservers/retriever/src/websearch_backends/exa_backend.py1CODE
LOWservers/retriever/src/websearch_backends/base.py1CODE
LOW…ers/retriever/src/websearch_backends/tavily_backend.py1CODE
LOWservers/prompt/src/prompt.py1CODE
LOWservers/generation/src/local_generation.py2CODE
LOWservers/router/src/router.py1CODE
LOWservers/router/src/router.py2CODE
LOWsrc/ultrarag/server.py3CODE
LOWsrc/ultrarag/server.py9CODE
LOWsrc/ultrarag/server.py14CODE
LOWsrc/ultrarag/server.py17CODE
Cross-File Repetition3 hits · 15 pts
SeverityFileLineSnippetContext
HIGHservers/reranker/src/reranker.py0remove banned keys and none values from dictionary. args: d: dictionary to filter banned: list of keys to remove returnsSTRING
HIGHservers/retriever/src/retriever.py0remove banned keys and none values from dictionary. args: d: dictionary to filter banned: list of keys to remove returnsSTRING
HIGHservers/generation/src/generation.py0remove banned keys and none values from dictionary. args: d: dictionary to filter banned: list of keys to remove returnsSTRING
Redundant / Tautological Comments9 hits · 11 pts
SeverityFileLineSnippetContext
LOWui/backend/pipeline_manager.py2348 # Write fileCOMMENT
LOWui/backend/pipeline_manager.py2378 # Check if old file existsCOMMENT
LOWui/backend/pipeline_manager.py2383 # Check if new name already exists in any known pipeline directoryCOMMENT
LOWservers/benchmark/src/benchmark.py89 # Check if ret is empty before accessing valuesCOMMENT
LOWservers/corpus/src/corpus.py43 # Check if safe_path is relative to base_pathCOMMENT
LOWservers/custom/src/custom.py986 # Check if already extendedCOMMENT
LOWsrc/ultrarag/client.py300 # Check if there are any branch*_state keysCOMMENT
LOWsrc/ultrarag/client.py1806 # Check if doc already has [id] prefixCOMMENT
LOWsrc/ultrarag/client.py1971 # Check if doc already has [id] prefixCOMMENT
Self-Referential Comments2 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUMui/backend/pipeline_manager.py3591 # Create a progress wrapper for streaming updatesCOMMENT
MEDIUMservers/prompt/src/prompt.py16# Create a sandboxed Jinja2 environment for securityCOMMENT
Modern Structural Boilerplate4 hits · 4 pts
SeverityFileLineSnippetContext
LOWservers/retriever/src/index_backends/__init__.py43__all__ = [CODE
LOWservers/retriever/src/websearch_backends/__init__.py43__all__ = [CODE
LOW⚡src/ultrarag/cli.py524__all__ = [STRING
LOWsrc/ultrarag/utils.py110def set_pdeathsig() -> None:CODE
AI Structural Patterns2 hits · 2 pts
SeverityFileLineSnippetContext
LOWsrc/ultrarag/server.py39CODE
LOWsrc/ultrarag/server.py244CODE