cnhkmcp 2.1.0__tar.gz → 2.1.1__tar.gz

{cnhkmcp-2.1.0/cnhkmcp.egg-info → cnhkmcp-2.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cnhkmcp
-Version: 2.1.0
+Version: 2.1.1
 Summary: A comprehensive Model Context Protocol (MCP) server for quantitative trading platform integration
 Home-page: https://github.com/cnhk/cnhkmcp
 Author: CNHK

{cnhkmcp-2.1.0 → cnhkmcp-2.1.1}/cnhkmcp/untracked/AI/346/241/214/351/235/242/346/217/222/344/273/266/main.py

@@ -4,7 +4,6 @@ import base64
 import tkinter as tk
 from tkinter import scrolledtext, messagebox, Toplevel
 from PIL import Image, ImageTk, ImageGrab
-import pyautogui
 from openai import OpenAI
 import threading
 import io
@@ -21,14 +20,10 @@ def install_dependencies():
     # Mapping of package names to their import names (if different)
     packages = {
         "openai": "openai",
-        "pyautogui": "pyautogui",
         "Pillow": "PIL",
-        "pyperclip": "pyperclip",
-        "keyboard": "keyboard",
         "fastembed": "fastembed",
         "chromadb": "chromadb",
         "watchdog": "watchdog",
-        "urllib3": "urllib3",
         "pypdf": "pypdf",
         "python-docx": "docx"
     }

{cnhkmcp-2.1.0 → cnhkmcp-2.1.1}/cnhkmcp/untracked/AI/346/241/214/351/235/242/346/217/222/344/273/266/rag_engine.py

@@ -34,6 +34,8 @@ class KnowledgeBase:
     def __init__(self, kb_path="knowledge", db_path="vector_db"):
         self.kb_path = os.path.abspath(kb_path)
         self.db_path = os.path.abspath(db_path)
+        self.meta_path = os.path.join(self.db_path, "_meta.json")
+        self.manifest_path = os.path.join(self.db_path, "_manifest.json")
         self._collection_reset_guard = False
         
         if not os.path.exists(self.kb_path):
@@ -71,6 +73,13 @@ class KnowledgeBase:
         # Store chosen model name for reference
         global MODEL_NAME
         MODEL_NAME = chosen
+
+        # Cache embedding dimension (detects library/model changes that corrupt existing indexes)
+        self.embed_dim = self._get_embedding_dim()
+        self.chroma_version = getattr(chromadb, "__version__", "unknown")
+
+        # If the stored index was built with a different model/dimension/chromadb version, wipe it
+        self._maybe_reset_for_incompatibility(chosen, self.embed_dim, self.chroma_version)
         
         # Initialize Vector DB
         self._init_collection()
@@ -85,19 +94,73 @@ class KnowledgeBase:
         """(Re)initialize Chroma client/collection. If recreate=True, wipe on-disk index."""
         if recreate and os.path.exists(self.db_path):
             shutil.rmtree(self.db_path, ignore_errors=True)
-        self.client = chromadb.PersistentClient(path=self.db_path)
-        self.collection = self.client.get_or_create_collection(
-            name=COLLECTION_NAME,
-            metadata={"hnsw:space": "cosine"}
-        )
+        try:
+            self.client = chromadb.PersistentClient(path=self.db_path)
+            self.collection = self.client.get_or_create_collection(
+                name=COLLECTION_NAME,
+                metadata={"hnsw:space": "cosine"}
+            )
+        except Exception as exc:
+            # If collection load itself fails, wipe and retry once to clear corrupted segments
+            if not recreate:
+                shutil.rmtree(self.db_path, ignore_errors=True)
+                return self._init_collection(recreate=True)
+            raise
+
+        # Persist metadata about the embedding model used to build this index
+        try:
+            os.makedirs(self.db_path, exist_ok=True)
+            with open(self.meta_path, "w", encoding="utf-8") as f:
+                json.dump({
+                    "model": MODEL_NAME,
+                    "embed_dim": self.embed_dim,
+                    "chroma_version": self.chroma_version,
+                }, f)
+        except Exception:
+            pass  # Metadata failure should not block runtime
+
+    def _maybe_reset_for_incompatibility(self, chosen_model: str, embed_dim: int, chroma_version: str):
+        """If existing index meta differs (model/dimension/chromadb), wipe it."""
+        if not os.path.exists(self.db_path):
+            return
+        try:
+            with open(self.meta_path, "r", encoding="utf-8") as f:
+                meta = json.load(f)
+            prev_model = meta.get("model")
+            prev_dim = meta.get("embed_dim")
+            prev_chroma = meta.get("chroma_version")
+            if prev_model != chosen_model or prev_dim != embed_dim or prev_chroma != chroma_version:
+                shutil.rmtree(self.db_path, ignore_errors=True)
+        except Exception:
+            # If meta cannot be read, assume stale/corrupted and rebuild
+            shutil.rmtree(self.db_path, ignore_errors=True)
+
+    def _get_embedding_dim(self) -> int:
+        for vec in self.model.embed(["dimension_probe"]):
+            try:
+                return len(vec)
+            except Exception:
+                return len(list(vec))
+        raise RuntimeError("Failed to determine embedding dimension")
 
     def sync_knowledge(self, allow_reset: bool = True):
         """Scans the knowledge folder and updates the vector database."""
         print("Syncing knowledge base...")
+        manifest = self._load_manifest()
+        updated_manifest = {}
         supported_extensions = (".txt", ".md", ".pdf", ".docx", ".json")
+        current_files = []
         for filename in os.listdir(self.kb_path):
             file_path = os.path.join(self.kb_path, filename)
             if os.path.isfile(file_path) and filename.lower().endswith(supported_extensions):
+                current_files.append(filename)
+                mtime = os.path.getmtime(file_path)
+                size = os.path.getsize(file_path)
+                prev_meta = manifest.get(filename)
+                # Skip unchanged files
+                if prev_meta and prev_meta.get("mtime") == mtime and prev_meta.get("size") == size:
+                    updated_manifest[filename] = prev_meta
+                    continue
                 try:
                     content = self._extract_text(file_path)
                     if content:
@@ -133,6 +196,7 @@ class KnowledgeBase:
                                 embeddings=embeddings
                             )
                             print(f"  ✓ Indexed {filename}: {len(original_chunks)} chunks")
+                            updated_manifest[filename] = {"mtime": mtime, "size": size}
                 except Exception as e:
                     err_msg = str(e)
                     print(f"Error processing {filename}: {err_msg}")
@@ -143,6 +207,16 @@ class KnowledgeBase:
                             self._collection_reset_guard = True
                             self._init_collection(recreate=True)
                             return self.sync_knowledge(allow_reset=False)
+        # Remove deleted files from the index
+        deleted_files = set(manifest.keys()) - set(current_files)
+        for filename in deleted_files:
+            try:
+                self.collection.delete(where={"source": filename})
+                print(f"  ✓ Removed deleted file from index: {filename}")
+            except Exception as e:
+                print(f"  ! Failed to remove {filename}: {e}")
+        # Persist manifest
+        self._save_manifest(updated_manifest)
         print("Knowledge base sync complete.")
 
     def _extract_text(self, file_path):
@@ -248,6 +322,23 @@ class KnowledgeBase:
         self.observer.schedule(event_handler, self.kb_path, recursive=False)
         self.observer.start()
 
+    def _load_manifest(self):
+        if not os.path.exists(self.manifest_path):
+            return {}
+        try:
+            with open(self.manifest_path, "r", encoding="utf-8") as f:
+                return json.load(f)
+        except Exception:
+            return {}
+
+    def _save_manifest(self, data):
+        try:
+            os.makedirs(self.db_path, exist_ok=True)
+            with open(self.manifest_path, "w", encoding="utf-8") as f:
+                json.dump(data, f, ensure_ascii=False, indent=2)
+        except Exception as e:
+            print(f"  ! Failed to save manifest: {e}")
+
 class KBHandler(FileSystemEventHandler):
     def __init__(self, kb_instance):
         self.kb = kb_instance

{cnhkmcp-2.1.0 → cnhkmcp-2.1.1}/cnhkmcp/untracked/AI/346/241/214/351/235/242/346/217/222/344/273/266/requirements.txt

@@ -1,12 +1,7 @@
 openai
-pyautogui
 Pillow
-pyperclip
-keyboard
 fastembed>=0.3.4
 chromadb>=0.5.0
 watchdog
-urllib3>=2.5.0
 pypdf
 python-docx
-pywin32

cnhkmcp-2.1.1/cnhkmcp/untracked/AI/346/241/214/351/235/242/346/217/222/344/273/266/vector_db/_manifest.json

@@ -0,0 +1,326 @@
+{
+  "001_10_Steps_to_Start_on_BRAIN_documentation.json": {
+    "mtime": 1767187226.1783848,
+    "size": 2483
+  },
+  "001_Intermediate_Pack_-_Improve_your_Alpha_2_2_documentation.json": {
+    "mtime": 1767187225.6750722,
+    "size": 9295
+  },
+  "001_Intermediate_Pack_-_Understand_Results_1_2_documentation.json": {
+    "mtime": 1767187225.1160033,
+    "size": 9758
+  },
+  "001_Introduction_to_Alphas_documentation.json": {
+    "mtime": 1767187223.7560995,
+    "size": 11156
+  },
+  "001_Introduction_to_BRAIN_Expression_Language_documentation.json": {
+    "mtime": 1767187224.277528,
+    "size": 4925
+  },
+  "001_WorldQuant_Challenge_documentation.json": {
+    "mtime": 1767187226.6850047,
+    "size": 4605
+  },
+  "001__Read_this_First_-_Starter_Pack_documentation.json": {
+    "mtime": 1767187223.2536645,
+    "size": 31286
+  },
+  "002_How_to_choose_the_Simulation_Settings_documentation.json": {
+    "mtime": 1767187228.2257776,
+    "size": 13775
+  },
+  "002_Simulate_your_first_Alpha_documentation.json": {
+    "mtime": 1767187227.7143147,
+    "size": 8701
+  },
+  "002__Alpha_Examples_for_Beginners_documentation.json": {
+    "mtime": 1767187229.1900375,
+    "size": 10826
+  },
+  "002__Alpha_Examples_for_Bronze_Users_documentation.json": {
+    "mtime": 1767187229.664476,
+    "size": 4795
+  },
+  "002__Alpha_Examples_for_Silver_Users_documentation.json": {
+    "mtime": 1767187230.1425803,
+    "size": 3854
+  },
+  "002__How_BRAIN_works_documentation.json": {
+    "mtime": 1767187228.7194252,
+    "size": 16929
+  },
+  "003_Clear_these_tests_before_submitting_an_Alpha_documentation.json": {
+    "mtime": 1767187231.1392078,
+    "size": 24609
+  },
+  "003_Parameters_in_the_Simulation_results_documentation.json": {
+    "mtime": 1767187231.8167577,
+    "size": 16168
+  },
+  "004_Group_Data_Fields_documentation.json": {
+    "mtime": 1767187234.323853,
+    "size": 4663
+  },
+  "004_How_to_use_the_Data_Explorer_documentation.json": {
+    "mtime": 1767187233.2908292,
+    "size": 6196
+  },
+  "004_Model77_dataset_documentation.json": {
+    "mtime": 1767187234.7999012,
+    "size": 3274
+  },
+  "004_Sentiment1_dataset_documentation.json": {
+    "mtime": 1767187235.2783144,
+    "size": 2058
+  },
+  "004_Understanding_Data_in_BRAIN_Key_Concepts_and_Tips_documentation.json": {
+    "mtime": 1767187232.782544,
+    "size": 9173
+  },
+  "004_Vector_Data_Fields_documentation.json": {
+    "mtime": 1767187233.8419762,
+    "size": 6058
+  },
+  "005_Crowding_Risk-Neutralized_Alphas_documentation.json": {
+    "mtime": 1767187239.4696057,
+    "size": 3404
+  },
+  "005_D0_documentation.json": {
+    "mtime": 1767187237.8772166,
+    "size": 5894
+  },
+  "005_Double_Neutralization_documentation.json": {
+    "mtime": 1767187237.2801647,
+    "size": 3308
+  },
+  "005_Fast_D1_Documentation_documentation.json": {
+    "mtime": 1767187244.849411,
+    "size": 11325
+  },
+  "005_Investability_Constrained_Metrics_documentation.json": {
+    "mtime": 1767187244.361986,
+    "size": 7971
+  },
+  "005_Must-read_posts_How_to_improve_your_Alphas_documentation.json": {
+    "mtime": 1767187236.2457168,
+    "size": 2781
+  },
+  "005_Neutralization_documentation.json": {
+    "mtime": 1767187236.7823203,
+    "size": 8962
+  },
+  "005_RAM_Risk-Neutralized_Alphas_documentation.json": {
+    "mtime": 1767187240.0576506,
+    "size": 4121
+  },
+  "005_Risk_Neutralization_Default_setting_documentation.json": {
+    "mtime": 1767187238.9658227,
+    "size": 3796
+  },
+  "005_Risk_Neutralized_Alphas_documentation.json": {
+    "mtime": 1767187238.4253874,
+    "size": 11617
+  },
+  "005_Statistical_Risk-Neutralized_Alphas_documentation.json": {
+    "mtime": 1767187240.5924916,
+    "size": 5663
+  },
+  "006_EUR_TOP2500_Universe_documentation.json": {
+    "mtime": 1767187247.5703416,
+    "size": 2248
+  },
+  "006_Getting_Started_China_Research_for_Consultants_Gold_documentation.json": {
+    "mtime": 1767187248.0169055,
+    "size": 8247
+  },
+  "006_Getting_started_on_Illiquid_Universes_Gold_documentation.json": {
+    "mtime": 1767187247.1297894,
+    "size": 2224
+  },
+  "006_Getting_started_with_USA_TOPSP500_universe_Gold_documentation.json": {
+    "mtime": 1767187246.6729863,
+    "size": 2681
+  },
+  "006_GLB_TOPDIV3000_Universe_documentation.json": {
+    "mtime": 1767187248.4504318,
+    "size": 2990
+  },
+  "006_Global_Alphas_Gold_documentation.json": {
+    "mtime": 1767187246.0390387,
+    "size": 5531
+  },
+  "006_India_Alphas_documentation.json": {
+    "mtime": 1767187248.8769279,
+    "size": 1845
+  },
+  "007_Consultant_Dos_and_Don_ts_documentation.json": {
+    "mtime": 1767187252.9861574,
+    "size": 6318
+  },
+  "007_Consultant_Features_documentation.json": {
+    "mtime": 1767187251.6508195,
+    "size": 16785
+  },
+  "007_Consultant_Simulation_Features_documentation.json": {
+    "mtime": 1767187251.177272,
+    "size": 7226
+  },
+  "007_Consultant_Submission_Tests_documentation.json": {
+    "mtime": 1767187252.1096609,
+    "size": 17040
+  },
+  "007_Finding_Consultant_Alphas_documentation.json": {
+    "mtime": 1767187250.6579707,
+    "size": 24560
+  },
+  "007_Power_Pool_Alphas_documentation.json": {
+    "mtime": 1767187250.1653683,
+    "size": 6398
+  },
+  "007_Research_Advisory_Program_documentation.json": {
+    "mtime": 1767187253.4177225,
+    "size": 2637
+  },
+  "007_Starting_Guide_for_Research_Consultants_documentation.json": {
+    "mtime": 1767187249.7283993,
+    "size": 3245
+  },
+  "007_Visualization_Tool_documentation.json": {
+    "mtime": 1767187252.5484178,
+    "size": 5744
+  },
+  "007_Your_Advisor_-_Kunqi_Jiang_documentation.json": {
+    "mtime": 1767187253.8533716,
+    "size": 4746
+  },
+  "007__Brain_Genius_documentation.json": {
+    "mtime": 1767187257.3133671,
+    "size": 16460
+  },
+  "007__Single_Dataset_Alphas_documentation.json": {
+    "mtime": 1767187256.8453045,
+    "size": 4113
+  },
+  "008_Advisory_Theme_Calendar_documentation.json": {
+    "mtime": 1767187259.502196,
+    "size": 584
+  },
+  "008_Multiplier_Rules_documentation.json": {
+    "mtime": 1767187258.6333888,
+    "size": 2178
+  },
+  "008_Overview_of_Themes_documentation.json": {
+    "mtime": 1767187258.1852746,
+    "size": 1784
+  },
+  "008_Theme_Calendar_documentation.json": {
+    "mtime": 1767187259.0729353,
+    "size": 8936
+  },
+  "009_Combo_Expression_documentation.json": {
+    "mtime": 1767187261.4117863,
+    "size": 10902
+  },
+  "009_Global_SuperAlphas_documentation.json": {
+    "mtime": 1767187263.181562,
+    "size": 3717
+  },
+  "009_Helpful_Tips_documentation.json": {
+    "mtime": 1767187262.3033876,
+    "size": 3618
+  },
+  "009_Selection_Expression_documentation.json": {
+    "mtime": 1767187260.918844,
+    "size": 47119
+  },
+  "009_SuperAlpha_Operators_documentation.json": {
+    "mtime": 1767187262.748049,
+    "size": 18735
+  },
+  "009_SuperAlpha_Results_documentation.json": {
+    "mtime": 1767187261.8593862,
+    "size": 3838
+  },
+  "009_What_is_a_SuperAlpha_documentation.json": {
+    "mtime": 1767187260.3861206,
+    "size": 13234
+  },
+  "010_BRAIN_API_documentation.json": {
+    "mtime": 1767187264.5490012,
+    "size": 36407
+  },
+  "010_Documentation_for_ACE_API_Library_Gold_documentation.json": {
+    "mtime": 1767187264.9810457,
+    "size": 1660
+  },
+  "010__Understanding_simulation_limits_documentation.json": {
+    "mtime": 1767187264.0576608,
+    "size": 12013
+  },
+  "arithmetic_operators.json": {
+    "mtime": 1767187265.4527013,
+    "size": 5302
+  },
+  "asi_datasets.json": {
+    "mtime": 1767187329.8343418,
+    "size": 241709
+  },
+  "chn_datasets.json": {
+    "mtime": 1767187329.8464715,
+    "size": 112139
+  },
+  "cross_sectional_operators.json": {
+    "mtime": 1767187265.454866,
+    "size": 3393
+  },
+  "eur_datasets.json": {
+    "mtime": 1767187329.8725038,
+    "size": 268981
+  },
+  "glb_datasets.json": {
+    "mtime": 1767187329.8975177,
+    "size": 222049
+  },
+  "group_operators.json": {
+    "mtime": 1767187265.4558804,
+    "size": 4058
+  },
+  "ind_datasets.json": {
+    "mtime": 1767187329.930282,
+    "size": 259819
+  },
+  "logical_operators.json": {
+    "mtime": 1767187265.4568646,
+    "size": 3549
+  },
+  "reduce_operators.json": {
+    "mtime": 1767187265.4588814,
+    "size": 8602
+  },
+  "special_operators.json": {
+    "mtime": 1767188164.9683514,
+    "size": 893
+  },
+  "test.txt": {
+    "mtime": 1767174050.546388,
+    "size": 82
+  },
+  "time_series_operators.json": {
+    "mtime": 1767187265.4623148,
+    "size": 12968
+  },
+  "transformational_operators.json": {
+    "mtime": 1767187265.4623148,
+    "size": 2080
+  },
+  "usa_datasets.json": {
+    "mtime": 1767187329.9605117,
+    "size": 402280
+  },
+  "vector_operators.json": {
+    "mtime": 1767187265.4637623,
+    "size": 997
+  }
+}

cnhkmcp-2.1.1/cnhkmcp/untracked/AI/346/241/214/351/235/242/346/217/222/344/273/266/vector_db/_meta.json

@@ -0,0 +1 @@
+{"model": "jinaai/jina-embeddings-v2-base-zh", "embed_dim": 768, "chroma_version": "1.4.0"}

{cnhkmcp-2.1.0 → cnhkmcp-2.1.1/cnhkmcp.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cnhkmcp
-Version: 2.1.0
+Version: 2.1.1
 Summary: A comprehensive Model Context Protocol (MCP) server for quantitative trading platform integration
 Home-page: https://github.com/cnhk/cnhkmcp
 Author: CNHK

{cnhkmcp-2.1.0 → cnhkmcp-2.1.1}/cnhkmcp.egg-info/SOURCES.txt

@@ -25,6 +25,7 @@ cnhkmcp/untracked/示例工作流_Dataset_Exploration_Expert_Manual.md
 cnhkmcp/untracked/示例工作流_daily_report_workflow.md
 cnhkmcp/untracked/配置前运行我_安装必要依赖包.py
 cnhkmcp/untracked/AI桌面插件/README.md
+cnhkmcp/untracked/AI桌面插件/ace.log
 cnhkmcp/untracked/AI桌面插件/config.json
 cnhkmcp/untracked/AI桌面插件/icon.ico
 cnhkmcp/untracked/AI桌面插件/icon.png
@@ -40,7 +41,10 @@ cnhkmcp/untracked/AI桌面插件/get_knowledgeBase_tool/fetch_all_documentation.
 cnhkmcp/untracked/AI桌面插件/get_knowledgeBase_tool/fetch_all_operators.py
 cnhkmcp/untracked/AI桌面插件/get_knowledgeBase_tool/helpful_functions.py
 cnhkmcp/untracked/AI桌面插件/knowledge/test.txt
+cnhkmcp/untracked/AI桌面插件/vector_db/_manifest.json
+cnhkmcp/untracked/AI桌面插件/vector_db/_meta.json
 cnhkmcp/untracked/AI桌面插件/vector_db/chroma.sqlite3
+cnhkmcp/untracked/AI桌面插件/vector_db/be5d957c-b724-46e3-91d1-999e9f5f7d28/index_metadata.pickle
 cnhkmcp/untracked/APP/.gitignore
 cnhkmcp/untracked/APP/MODULAR_STRUCTURE.md
 cnhkmcp/untracked/APP/README.md

{cnhkmcp-2.1.0 → cnhkmcp-2.1.1}/setup.py

@@ -13,7 +13,7 @@ def read_requirements():
 
 setup(
     name="cnhkmcp",
-    version="2.1.0",
+    version="2.1.1",
     author="CNHK",
     author_email="cnhk@example.com",
     description="A comprehensive Model Context Protocol (MCP) server for quantitative trading platform integration",