union-app-chat-stream 1.0.3

package/.gitignore

@@ -0,0 +1,16 @@
+.idea/
+.venv/
+.chroma/
+__pycache__/
+deploy/scripts/union_py/
+data/
+# Ignore virtual environment files
+*.pyc
+.DS_Store
+.env
+.env.*
+
+# Knowledge base (RAG documents, managed separately)
+# Ignore everything in knowledge/ but keep the directory via .gitkeep
+knowledge/*
+!knowledge/.gitkeep

package/PROJECT_OVERVIEW.md

@@ -0,0 +1,187 @@
+# Project Overview
+
+## Purpose
+
+This repository contains a Python 3.12 Flask application for Union operations
+chat and RAG-assisted troubleshooting. It exposes streaming chat APIs, runtime
+management APIs, and a health check endpoint. The app is intended to run behind
+Hypercorn in Linux x86_64 deployment environments.
+
+## Stack
+
+- Language: Python 3.12
+- Web framework: Flask running through Hypercorn ASGI
+- LLM SDK: zai-sdk
+- Vector database: ChromaDB
+- Validation: Pydantic v2
+- Logging: Loguru
+- Runtime target: Linux x86_64
+
+## Repository Layout
+
+```text
+union-py-app/
+├── app/                         # Flask application package
+│   ├── __init__.py              # create_app() factory and blueprint setup
+│   ├── wsgi.py                  # Application entrypoint
+│   ├── authenticated_user.py    # Session authentication middleware
+│   ├── config/                  # Configuration and logging
+│   ├── manager/                 # Business orchestration layer
+│   ├── models/                  # Pydantic schemas
+│   ├── service/                 # Core services: chat, RAG, LLM, union logic
+│   ├── utils/                   # Shared utility functions
+│   └── views/                   # Flask blueprints and HTTP routes
+├── knowledge/                   # RAG knowledge source files
+├── tools/                       # Tool definitions for model tool calling
+├── scripts/                     # Environment-specific launcher scripts
+├── deploy/                      # Deployment config, templates, and scripts
+├── requirements.txt             # Python dependencies
+├── ci.yml                       # CI configuration
+└── .gitignore
+```
+
+Project-specific context belongs in this file. Do not add a repository-root
+`AGENTS.md`; global working rules are provided outside the repo.
+
+## Important Modules
+
+- `app/__init__.py`: Builds the Flask app, loads configuration, initializes
+  managers in `app.extensions`, and registers blueprints.
+- `app/wsgi.py`: Imports `create_app()` and exposes `app` for Hypercorn.
+- `app/authenticated_user.py`: Validates login identity before requests.
+- `app/config/env_config.py`: Defines Flask configuration values.
+- `app/config/logger_config.py`: Initializes application logging.
+- `app/manager/chatstream_manager.py`: Orchestrates chatstream routes, including
+  chat streaming and RAG status/rebuild operations.
+- `app/manager/runtime_manager.py`: Handles runtime management behavior.
+- `app/manager/prompts.py`: Stores prompt templates.
+- `app/models/schemas.py`: Defines request and response schemas.
+- `app/service/chat_service.py`: Implements streaming chat and tool-call loops.
+- `app/service/rag_service.py`: Manages RAG indexing and retrieval.
+- `app/service/llm_service.py`: Wraps LLM provider behavior.
+- `app/service/union_service.py`: Contains Union operations business services.
+- `app/utils/function_utils.py`: Loads YAML tool definitions and dispatches
+  tool calls.
+- `app/views/view_chatstream.py`: Chatstream and RAG HTTP endpoints.
+- `app/views/view_runtime.py`: Runtime HTTP endpoints.
+- `app/views/view_healthcheck.py`: Health check HTTP endpoint.
+
+## API Surface
+
+| Method | Path | Blueprint | Purpose |
+|---|---|---|---|
+| POST | `/chatstream/v1/chat/stream` | chatstream | SSE streaming chat with RAG and tool calls |
+| GET | `/chatstream/v1/rag/check` | chatstream | RAG knowledge and vector database status |
+| POST | `/chatstream/v1/rag/force-rebuild` | chatstream | Force rebuild of the RAG knowledge base |
+| GET | `/healthcheck.html` | healthcheck | Service health check |
+
+## Environment Loading
+
+Environment-specific launch scripts under `scripts/` contain the target
+environment name on the first line:
+
+- `scripts/start-BJ11.sh`: `prod.bj11`
+- `scripts/start-BJ12.sh`: `test.bj12`
+- `scripts/start-SH20.sh`: `prod.sh20`
+- `scripts/start-SZ31.sh`: `prod.sz31`
+
+The deploy launcher at `deploy/scripts/start.sh` reads that environment name,
+exports `FLASK_ENV`, and starts the app through Hypercorn.
+
+Environment files live under `app/` and are intentionally ignored by Git:
+
+- `app/.env`
+- `app/.env.dev`
+- `app/.env.prod.bj11`
+- `app/.env.prod.sh20`
+- `app/.env.prod.sz31`
+- `app/.env.test.bj12`
+
+Treat all environment files, credentials, tokens, and production configuration
+as sensitive. Do not commit them.
+
+## Deployment
+
+Deployment files are organized under `deploy/`:
+
+- `deploy/autoconf.yml`: Autoconf mapping for deployment environments.
+- `deploy/autoconf/templates/env.j2`: Template used to render environment
+  variables.
+- `deploy/scripts/start.sh`: Creates or uses a virtual environment, installs
+  dependencies, and starts Hypercorn.
+- `deploy/scripts/stop.sh`: Stops the Hypercorn process.
+- `deploy/scripts/healthcheck.sh`: Deployment health check entrypoint.
+- `deploy/scripts/requirements.txt`: Deployment dependency file. It should stay
+  in sync with root `requirements.txt`.
+- `deploy/offline-packages/`: Expected location for offline wheel packages when
+  building a fully offline deployment bundle.
+
+## Development Notes
+
+- Read this file before changing project code.
+- Keep changes scoped to the requested behavior.
+- Prefer existing package boundaries: views call managers or services; services
+  contain core business logic; utils stay generic.
+- Keep RAG knowledge content under `knowledge/`. The directory is tracked using
+  `.gitkeep`; knowledge documents are managed separately and ignored by default.
+- Keep tool-call schema changes in `tools/tool_definitions.yaml` aligned with
+  `app/utils/function_utils.py` and the services that implement tools.
+- Avoid committing generated caches, virtual environments, local environment
+  files, or machine-specific artifacts.
+- Before publishing this project to npm, bump the package version forward and
+  verify the packed artifact includes the full `app/`, `tools/`, and
+  `knowledge/` directories plus `deploy/` excluding `deploy/offline-packages/`;
+  keep the existing `.gitignore` rule that ignores local `knowledge/` files.
+- npm publishes must include `app/.env*` environment files, but only after
+  temporarily masking every sensitive value in those files, including keys,
+  URLs, tokens, secrets, cookies, passwords, and values that expose business
+  terms such as `网联`, `网联清算`, `nucc`, `uops`, or `联合运维`. After the npm
+  publish finishes, restore the local `.env*` files back to their original
+  plaintext values and remove the temporary masking changes.
+- Keep `app/.env*` files human-editable: preserve their key order, comments,
+  and blank-line grouping when normalizing, masking, or restoring them.
+
+## GLM Model Capability Reference
+
+- Use `/Users/simon/Documents/glm-model-doc.md` as the local long-term reference
+  for GLM model capabilities. When a change or design decision depends on GLM
+  behavior such as Thinking, Interleaved Thinking, Preserved Thinking,
+  turn-level thinking, streaming, function calling, tool streaming, or agent
+  loops, read that document before assuming API behavior.
+- For complex chat, RAG, or tool-call work, prefer designs that match GLM's
+  native tool-calling and thinking model instead of adding ad hoc orchestration
+  first. In particular, RAG can be exposed as a normal tool when the model needs
+  to decide search intent from conversation history.
+- When using GLM Thinking with tools, preserve the model's `reasoning_content`
+  according to the document's requirements. Interleaved thinking allows the
+  model to continue reasoning between tool calls and after tool results; for
+  preserved thinking, pass complete, unmodified reasoning content back in later
+  messages and use `clear_thinking: false` where applicable.
+- Do not rely on prompt text alone for critical tool hierarchy or evidence
+  policy. Keep executable tool definitions in `tools/tool_definitions.yaml`, and
+  treat knowledge-base "related functions" as routing hints unless code
+  explicitly promotes them to executable tools.
+
+## Validation
+
+Use the smallest reliable checks that cover the change:
+
+- Syntax check: `python3 -m compileall app`
+- RAG smoke check when touching RAG code:
+  `python3 -c "from app import create_app; app = create_app(); print(app.extensions['chatstream_manager'].check_rag())"`
+- Endpoint smoke checks should cover `/healthcheck.html` and the relevant
+  `/chatstream/v1/*` route when route behavior changes.
+- When dependency files change, verify root `requirements.txt` and
+  `deploy/scripts/requirements.txt` stay aligned.
+
+## Known Structure Gaps To Confirm
+
+These are structure differences observed during the initial repository check:
+
+- `deploy/offline-packages/` is expected by the original structure but is not
+  currently present.
+- Shell scripts are present but may need executable permissions for deployment.
+- `tools/tool_definitions.yaml` currently exists but may need project-specific
+  tool definitions populated.
+- `scripts/healthcheck.sh` and `deploy/scripts/healthcheck.sh` currently exist
+  but may need health check logic populated.

package/app/.env

@@ -0,0 +1,63 @@
+# Flask and request authentication
+SECRET_KEY=<MASKED_SECRET>
+
+# External API endpoints
+GET_USE_INFO_URL=<MASKED_URL>
+GET_ORG_INFO_URL=<MASKED_URL>
+GET_JIRA_INFO_URL=<MASKED_URL>
+GET_BIGDATA_URL=<MASKED_URL>
+GET_UNION_BASE_URL=<MASKED_URL>
+
+# Legacy external API tokens
+GET_ORG_INFO_URL_TOKEN=<MASKED_TOKEN>
+GET_JIRA_INFO_URL_TOKEN=<MASKED_TOKEN>
+
+# Authorization and logging
+PERMISSIONS=
+LOG_LEVEL=INFO
+CONSOLE_STDOUT=TRUE
+LOG_DIR=/data/appLogs
+
+# Runtime environment and JWT
+FLASK_ENV=dev
+JWT_SECRET_KEY=<MASKED_SECRET>
+JWT_EXPIRATION_SECOND=900
+JWT_RENEW_SECOND=700
+
+# LLM provider
+LLM_URL=<MASKED_URL>
+LLM_KEY=<MASKED_KEY>
+LLM_MODEL=GLM-4.7-Flash
+LLM_MAX_TOKENS=4096
+LLM_TEMPERATURE=0.7
+LLM_TOP_P=0.9
+
+# Chat behavior
+SYSTEM_PROMPT=<MASKED_BUSINESS_VALUE>
+
+# Business filter
+FILTER_ENABLED=false
+FILTER_ALLOWED_KEYWORDS=<MASKED_BUSINESS_VALUE>
+FILTER_REJECTION_MESSAGE=<MASKED_BUSINESS_VALUE>
+
+# Tool and conversation settings
+TOOLS_MAX_ROUNDS=5
+CONVERSATION_MAX_HISTORY=20
+CONVERSATION_TTL=3600
+
+# RAG settings
+RAG_ENABLED=true
+RAG_KNOWLEDGE_DIR=knowledge
+RAG_PERSIST_DIR=.chroma
+RAG_COLLECTION=ops_knowledge
+RAG_EMBEDDING_MODEL=embedding-3
+RAG_EMBEDDING_MAX_CHARS=6000
+RAG_EMBEDDING_BATCH_SIZE=8
+RAG_TOP_K=5
+RAG_SEMANTIC_CANDIDATE_K=40
+RAG_CONTEXT_K=8
+RAG_EXACT_CONTEXT_K=3
+RAG_EXACT_PER_FILE_CONTEXT_K=1
+RAG_PER_FILE_CONTEXT_K=2
+RAG_CHUNK_SIZE=1200
+RAG_REBUILD_ON_STARTUP=false

package/app/.env.dev

@@ -0,0 +1,63 @@
+# Flask and request authentication
+SECRET_KEY=<MASKED_SECRET>
+
+# External API endpoints
+GET_USE_INFO_URL=<MASKED_URL>
+GET_ORG_INFO_URL=<MASKED_URL>
+GET_JIRA_INFO_URL=<MASKED_URL>
+GET_BIGDATA_URL=<MASKED_URL>
+GET_UNION_BASE_URL=<MASKED_URL>
+
+# Legacy external API tokens
+GET_ORG_INFO_URL_TOKEN=<MASKED_TOKEN>
+GET_JIRA_INFO_URL_TOKEN=<MASKED_TOKEN>
+
+# Authorization and logging
+PERMISSIONS=
+LOG_LEVEL=INFO
+CONSOLE_STDOUT=TRUE
+LOG_DIR=/Users/simon/code/union-py-app/data/appLogs
+
+# Runtime environment and JWT
+FLASK_ENV=dev
+JWT_SECRET_KEY=<MASKED_SECRET>
+JWT_EXPIRATION_SECOND=900
+JWT_RENEW_SECOND=700
+
+# LLM provider
+LLM_URL=<MASKED_URL>
+LLM_KEY=<MASKED_KEY>
+LLM_MODEL=GLM-4.7-Flash
+LLM_MAX_TOKENS=4096
+LLM_TEMPERATURE=0.7
+LLM_TOP_P=0.9
+
+# Chat behavior
+SYSTEM_PROMPT=<MASKED_BUSINESS_VALUE>
+
+# Business filter
+FILTER_ENABLED=false
+FILTER_ALLOWED_KEYWORDS=<MASKED_BUSINESS_VALUE>
+FILTER_REJECTION_MESSAGE=<MASKED_BUSINESS_VALUE>
+
+# Tool and conversation settings
+TOOLS_MAX_ROUNDS=5
+CONVERSATION_MAX_HISTORY=20
+CONVERSATION_TTL=3600
+
+# RAG settings
+RAG_ENABLED=true
+RAG_KNOWLEDGE_DIR=knowledge
+RAG_PERSIST_DIR=.chroma
+RAG_COLLECTION=ops_knowledge
+RAG_EMBEDDING_MODEL=embedding-3
+RAG_EMBEDDING_MAX_CHARS=6000
+RAG_EMBEDDING_BATCH_SIZE=8
+RAG_TOP_K=5
+RAG_SEMANTIC_CANDIDATE_K=40
+RAG_CONTEXT_K=8
+RAG_EXACT_CONTEXT_K=3
+RAG_EXACT_PER_FILE_CONTEXT_K=1
+RAG_PER_FILE_CONTEXT_K=2
+RAG_CHUNK_SIZE=1200
+RAG_REBUILD_ON_STARTUP=false

package/app/.env.prod.bj11

@@ -0,0 +1,63 @@
+# Flask and request authentication
+SECRET_KEY=<MASKED_SECRET>
+
+# External API endpoints
+GET_USE_INFO_URL=<MASKED_URL>
+GET_ORG_INFO_URL=<MASKED_URL>
+GET_JIRA_INFO_URL=<MASKED_URL>
+GET_BIGDATA_URL=<MASKED_URL>
+GET_UNION_BASE_URL=<MASKED_URL>
+
+# Legacy external API tokens
+GET_ORG_INFO_URL_TOKEN=<MASKED_TOKEN>
+GET_JIRA_INFO_URL_TOKEN=<MASKED_TOKEN>
+
+# Authorization and logging
+PERMISSIONS=
+LOG_LEVEL=INFO
+CONSOLE_STDOUT=FALSE
+LOG_DIR=/data/appLogs
+
+# Runtime environment and JWT
+FLASK_ENV=prod.bj11
+JWT_SECRET_KEY=<MASKED_SECRET>
+JWT_EXPIRATION_SECOND=900
+JWT_RENEW_SECOND=700
+
+# LLM provider
+LLM_URL=<MASKED_URL>
+LLM_KEY=<MASKED_KEY>
+LLM_MODEL=glm-5
+LLM_MAX_TOKENS=4096
+LLM_TEMPERATURE=0.7
+LLM_TOP_P=0.9
+
+# Chat behavior
+SYSTEM_PROMPT=<MASKED_BUSINESS_VALUE>
+
+# Business filter
+FILTER_ENABLED=false
+FILTER_ALLOWED_KEYWORDS=<MASKED_BUSINESS_VALUE>
+FILTER_REJECTION_MESSAGE=<MASKED_BUSINESS_VALUE>
+
+# Tool and conversation settings
+TOOLS_MAX_ROUNDS=5
+CONVERSATION_MAX_HISTORY=20
+CONVERSATION_TTL=3600
+
+# RAG settings
+RAG_ENABLED=true
+RAG_KNOWLEDGE_DIR=knowledge
+RAG_PERSIST_DIR=.chroma
+RAG_COLLECTION=ops_knowledge
+RAG_EMBEDDING_MODEL=embedding-3
+RAG_EMBEDDING_MAX_CHARS=6000
+RAG_EMBEDDING_BATCH_SIZE=8
+RAG_TOP_K=5
+RAG_SEMANTIC_CANDIDATE_K=40
+RAG_CONTEXT_K=8
+RAG_EXACT_CONTEXT_K=3
+RAG_EXACT_PER_FILE_CONTEXT_K=1
+RAG_PER_FILE_CONTEXT_K=2
+RAG_CHUNK_SIZE=1200
+RAG_REBUILD_ON_STARTUP=false

package/app/.env.prod.sh20

@@ -0,0 +1,63 @@
+# Flask and request authentication
+SECRET_KEY=<MASKED_SECRET>
+
+# External API endpoints
+GET_USE_INFO_URL=<MASKED_URL>
+GET_ORG_INFO_URL=<MASKED_URL>
+GET_JIRA_INFO_URL=<MASKED_URL>
+GET_BIGDATA_URL=<MASKED_URL>
+GET_UNION_BASE_URL=<MASKED_URL>
+
+# Legacy external API tokens
+GET_ORG_INFO_URL_TOKEN=<MASKED_TOKEN>
+GET_JIRA_INFO_URL_TOKEN=<MASKED_TOKEN>
+
+# Authorization and logging
+PERMISSIONS=
+LOG_LEVEL=INFO
+CONSOLE_STDOUT=FALSE
+LOG_DIR=/data/appLogs
+
+# Runtime environment and JWT
+FLASK_ENV=prod.sh20
+JWT_SECRET_KEY=<MASKED_SECRET>
+JWT_EXPIRATION_SECOND=900
+JWT_RENEW_SECOND=700
+
+# LLM provider
+LLM_URL=<MASKED_URL>
+LLM_KEY=<MASKED_KEY>
+LLM_MODEL=glm-5
+LLM_MAX_TOKENS=4096
+LLM_TEMPERATURE=0.7
+LLM_TOP_P=0.9
+
+# Chat behavior
+SYSTEM_PROMPT=<MASKED_BUSINESS_VALUE>
+
+# Business filter
+FILTER_ENABLED=false
+FILTER_ALLOWED_KEYWORDS=<MASKED_BUSINESS_VALUE>
+FILTER_REJECTION_MESSAGE=<MASKED_BUSINESS_VALUE>
+
+# Tool and conversation settings
+TOOLS_MAX_ROUNDS=5
+CONVERSATION_MAX_HISTORY=20
+CONVERSATION_TTL=3600
+
+# RAG settings
+RAG_ENABLED=true
+RAG_KNOWLEDGE_DIR=knowledge
+RAG_PERSIST_DIR=.chroma
+RAG_COLLECTION=ops_knowledge
+RAG_EMBEDDING_MODEL=embedding-3
+RAG_EMBEDDING_MAX_CHARS=6000
+RAG_EMBEDDING_BATCH_SIZE=8
+RAG_TOP_K=5
+RAG_SEMANTIC_CANDIDATE_K=40
+RAG_CONTEXT_K=8
+RAG_EXACT_CONTEXT_K=3
+RAG_EXACT_PER_FILE_CONTEXT_K=1
+RAG_PER_FILE_CONTEXT_K=2
+RAG_CHUNK_SIZE=1200
+RAG_REBUILD_ON_STARTUP=false

package/app/.env.prod.sz31

@@ -0,0 +1,63 @@
+# Flask and request authentication
+SECRET_KEY=<MASKED_SECRET>
+
+# External API endpoints
+GET_USE_INFO_URL=<MASKED_URL>
+GET_ORG_INFO_URL=<MASKED_URL>
+GET_JIRA_INFO_URL=<MASKED_URL>
+GET_BIGDATA_URL=<MASKED_URL>
+GET_UNION_BASE_URL=<MASKED_URL>
+
+# Legacy external API tokens
+GET_ORG_INFO_URL_TOKEN=<MASKED_TOKEN>
+GET_JIRA_INFO_URL_TOKEN=<MASKED_TOKEN>
+
+# Authorization and logging
+PERMISSIONS=
+LOG_LEVEL=INFO
+CONSOLE_STDOUT=FALSE
+LOG_DIR=/data/appLogs
+
+# Runtime environment and JWT
+FLASK_ENV=prod.sz31
+JWT_SECRET_KEY=<MASKED_SECRET>
+JWT_EXPIRATION_SECOND=900
+JWT_RENEW_SECOND=700
+
+# LLM provider
+LLM_URL=<MASKED_URL>
+LLM_KEY=<MASKED_KEY>
+LLM_MODEL=glm-5
+LLM_MAX_TOKENS=4096
+LLM_TEMPERATURE=0.7
+LLM_TOP_P=0.9
+
+# Chat behavior
+SYSTEM_PROMPT=<MASKED_BUSINESS_VALUE>
+
+# Business filter
+FILTER_ENABLED=false
+FILTER_ALLOWED_KEYWORDS=<MASKED_BUSINESS_VALUE>
+FILTER_REJECTION_MESSAGE=<MASKED_BUSINESS_VALUE>
+
+# Tool and conversation settings
+TOOLS_MAX_ROUNDS=5
+CONVERSATION_MAX_HISTORY=20
+CONVERSATION_TTL=3600
+
+# RAG settings
+RAG_ENABLED=true
+RAG_KNOWLEDGE_DIR=knowledge
+RAG_PERSIST_DIR=.chroma
+RAG_COLLECTION=ops_knowledge
+RAG_EMBEDDING_MODEL=embedding-3
+RAG_EMBEDDING_MAX_CHARS=6000
+RAG_EMBEDDING_BATCH_SIZE=8
+RAG_TOP_K=5
+RAG_SEMANTIC_CANDIDATE_K=40
+RAG_CONTEXT_K=8
+RAG_EXACT_CONTEXT_K=3
+RAG_EXACT_PER_FILE_CONTEXT_K=1
+RAG_PER_FILE_CONTEXT_K=2
+RAG_CHUNK_SIZE=1200
+RAG_REBUILD_ON_STARTUP=false

package/app/.env.test.bj12

@@ -0,0 +1,63 @@
+# Flask and request authentication
+SECRET_KEY=<MASKED_SECRET>
+
+# External API endpoints
+GET_USE_INFO_URL=<MASKED_URL>
+GET_ORG_INFO_URL=<MASKED_URL>
+GET_JIRA_INFO_URL=<MASKED_URL>
+GET_BIGDATA_URL=<MASKED_URL>
+GET_UNION_BASE_URL=<MASKED_URL>
+
+# Legacy external API tokens
+GET_ORG_INFO_URL_TOKEN=<MASKED_TOKEN>
+GET_JIRA_INFO_URL_TOKEN=<MASKED_TOKEN>
+
+# Authorization and logging
+PERMISSIONS=
+LOG_LEVEL=INFO
+CONSOLE_STDOUT=FALSE
+LOG_DIR=/data/appLogs
+
+# Runtime environment and JWT
+FLASK_ENV=test.prod.bj12
+JWT_SECRET_KEY=<MASKED_SECRET>
+JWT_EXPIRATION_SECOND=900
+JWT_RENEW_SECOND=700
+
+# LLM provider
+LLM_URL=<MASKED_URL>
+LLM_KEY=<MASKED_KEY>
+LLM_MODEL=glm-5
+LLM_MAX_TOKENS=4096
+LLM_TEMPERATURE=0.7
+LLM_TOP_P=0.9
+
+# Chat behavior
+SYSTEM_PROMPT=<MASKED_BUSINESS_VALUE>
+
+# Business filter
+FILTER_ENABLED=false
+FILTER_ALLOWED_KEYWORDS=<MASKED_BUSINESS_VALUE>
+FILTER_REJECTION_MESSAGE=<MASKED_BUSINESS_VALUE>
+
+# Tool and conversation settings
+TOOLS_MAX_ROUNDS=5
+CONVERSATION_MAX_HISTORY=20
+CONVERSATION_TTL=3600
+
+# RAG settings
+RAG_ENABLED=true
+RAG_KNOWLEDGE_DIR=knowledge
+RAG_PERSIST_DIR=.chroma
+RAG_COLLECTION=ops_knowledge
+RAG_EMBEDDING_MODEL=embedding-3
+RAG_EMBEDDING_MAX_CHARS=6000
+RAG_EMBEDDING_BATCH_SIZE=8
+RAG_TOP_K=5
+RAG_SEMANTIC_CANDIDATE_K=40
+RAG_CONTEXT_K=8
+RAG_EXACT_CONTEXT_K=3
+RAG_EXACT_PER_FILE_CONTEXT_K=1
+RAG_PER_FILE_CONTEXT_K=2
+RAG_CHUNK_SIZE=1200
+RAG_REBUILD_ON_STARTUP=false

package/app/__init__.py

@@ -0,0 +1,42 @@
+import os
+
+from flask import Flask
+from dotenv import load_dotenv
+
+
+def _load_dotenv_for_env():
+    config_name = os.getenv("FLASK_ENV", "dev")
+    dotenv_file = os.path.join(os.path.dirname(__file__), f".env.{config_name}")
+    load_dotenv(dotenv_file, override=True, verbose=True)
+
+
+def create_app():
+    _load_dotenv_for_env()
+
+    app = Flask(__name__)
+    from app.config.env_config import Config
+    app.config.from_object(Config)
+
+    from .authenticated_user import FlaskSessionClient
+    FlaskSessionClient(app)
+
+    from app.manager.chatstream_manager import ChatstreamManager
+    from app.manager.runtime_manager import RuntimeManager
+    from app.service.chat_service import ChatService
+    from app.service.llm_service import llm_service
+    from app.service.rag_service import RagService
+    from app.service.union_service import union_service
+
+    llm_service.initialize(app.config)
+    union_service.initialize(app.config)
+    rag_service = RagService(app.config)
+    chat_service = ChatService(app.config, rag_service, union_service)
+
+    app.extensions["chatstream_manager"] = ChatstreamManager(app.config, chat_service, rag_service)
+    app.extensions["runtime_manager"] = RuntimeManager(union_service, llm_service)
+
+    from .views import blueprints
+
+    for bp in blueprints:
+        app.register_blueprint(bp)
+    return app