memorizz 0.0.1__tar.gz

memorizz-0.0.1/PKG-INFO

@@ -0,0 +1,118 @@
+Metadata-Version: 2.3
+Name: memorizz
+Version: 0.0.1
+Summary: A memory management library for Python
+Project-URL: Homepage, https://github.com/RichmondAlake/memorizz
+Project-URL: Bug Tracker, https://github.com/yourusername/memorizz/issues
+Author-email: Richmond Alake <richmond.alake@gmail.com>
+License-File: LICENCE.txt
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.7
+Description-Content-Type: text/markdown
+
+MemoRizz is a comprehensive library for AI-assisted tools and functionalities. It currently includes MongoDB tools for storing function definitions and performing customizable vector searches.
+
+## Installation
+
+```
+pip install memorizz
+```
+
+## Usage
+
+MemoRizz can be used with either a custom configuration or the default settings. Here are examples of both approaches:
+
+### Using Custom Configuration
+
+```python
+from memorizz.databases.mongodb import MongoDBTools, MongoDBToolsConfig, mongodb_toolbox
+
+# Create a custom configuration
+custom_config = MongoDBToolsConfig(
+    mongo_uri="mongodb://custom-uri:27017",
+    db_name="my_custom_db",
+    collection_name="my_custom_tools",
+    embedding_model="text-embedding-ada-002",
+    vector_search_candidates=200,
+    vector_index_name="my_custom_index"
+)
+
+# Initialize MongoDBTools with custom configuration
+custom_mongo_tools = MongoDBTools(custom_config)
+
+# Use the custom mongodb_toolbox decorator
+@custom_mongo_tools.mongodb_toolbox()
+def custom_function(param1: str, param2: int) -> str:
+    """
+    This is a custom function using a custom configuration.
+    """
+    return f"Custom processed {param1} with {param2}"
+
+# Use the custom tools
+user_query = "How do I process something custom?"
+custom_tools = custom_mongo_tools.populate_tools(user_query, num_tools=3)
+
+print("Custom tools:", custom_tools)
+```
+
+### Using Default Configuration
+
+```python
+from memorizz.databases.mongodb import mongodb_toolbox, MongoDBTools
+
+# Use the default mongodb_toolbox decorator
+@mongodb_toolbox()
+def default_function(param1: str, param2: int) -> str:
+    """
+    This is a default function using the default configuration.
+    """
+    return f"Default processed {param1} with {param2}"
+
+# Use the default tools
+default_mongo_tools = MongoDBTools()  # This uses the default configuration
+user_query = "How do I process something with default settings?"
+default_tools = default_mongo_tools.populate_tools(user_query, num_tools=2)
+
+print("Default tools:", default_tools)
+```
+
+In both cases, the `mongodb_toolbox` decorator is used to register functions, and the `populate_tools` method is used to retrieve relevant tools based on a user query. The main difference is in the setup and configuration.
+
+The custom configuration approach allows you to specify your own MongoDB URI, database name, collection name, and other settings. This is useful when you need to connect to a specific MongoDB instance or customize the behavior of the tools.
+
+The default configuration approach is simpler and requires less setup. It's suitable for quick starts or when the default settings meet your needs.
+
+Choose the approach that best fits your project requirements and structure.
+
+## Features
+
+- MongoDB Tools:
+  - Automatic tool registration with MongoDB
+  - Vector search based on user queries
+  - Customizable number of tools returned
+  - Configurable embedding model and search parameters
+  - Error handling and logging
+- Extensible structure for future database support
+
+
+## Feature Roadmap
+
+- [x] Implement basic MongoDB tools functionality
+- [x] Add customizable vector search
+- [x] Implement error handling and logging
+- [x] Create PyPI package
+- [x] Restructure package for extensibility to other databases
+- [ ] Add support for multiple embedding models to make MongoDBToolsConfig embedding model agnostic
+- [ ] Implement MemScore logic for improved tool ranking and memory component retrival
+- [ ] Add async support for improved performance
+- [ ] Implement caching mechanism for embeddings and search results
+- [ ] Create comprehensive API documentation
+- [ ] Implement automated testing suite with high coverage
+- [ ] Create example projects and use cases
+- [ ] Add support for additional databases (e.g., PostgreSQL, Redis)
+
+## License
+
+This project is licensed under the MIT License.

memorizz-0.0.1/README.md

@@ -0,0 +1,104 @@
+MemoRizz is a comprehensive library for AI-assisted tools and functionalities. It currently includes MongoDB tools for storing function definitions and performing customizable vector searches.
+
+## Installation
+
+```
+pip install memorizz
+```
+
+## Usage
+
+MemoRizz can be used with either a custom configuration or the default settings. Here are examples of both approaches:
+
+### Using Custom Configuration
+
+```python
+from memorizz.databases.mongodb import MongoDBTools, MongoDBToolsConfig, mongodb_toolbox
+
+# Create a custom configuration
+custom_config = MongoDBToolsConfig(
+    mongo_uri="mongodb://custom-uri:27017",
+    db_name="my_custom_db",
+    collection_name="my_custom_tools",
+    embedding_model="text-embedding-ada-002",
+    vector_search_candidates=200,
+    vector_index_name="my_custom_index"
+)
+
+# Initialize MongoDBTools with custom configuration
+custom_mongo_tools = MongoDBTools(custom_config)
+
+# Use the custom mongodb_toolbox decorator
+@custom_mongo_tools.mongodb_toolbox()
+def custom_function(param1: str, param2: int) -> str:
+    """
+    This is a custom function using a custom configuration.
+    """
+    return f"Custom processed {param1} with {param2}"
+
+# Use the custom tools
+user_query = "How do I process something custom?"
+custom_tools = custom_mongo_tools.populate_tools(user_query, num_tools=3)
+
+print("Custom tools:", custom_tools)
+```
+
+### Using Default Configuration
+
+```python
+from memorizz.databases.mongodb import mongodb_toolbox, MongoDBTools
+
+# Use the default mongodb_toolbox decorator
+@mongodb_toolbox()
+def default_function(param1: str, param2: int) -> str:
+    """
+    This is a default function using the default configuration.
+    """
+    return f"Default processed {param1} with {param2}"
+
+# Use the default tools
+default_mongo_tools = MongoDBTools()  # This uses the default configuration
+user_query = "How do I process something with default settings?"
+default_tools = default_mongo_tools.populate_tools(user_query, num_tools=2)
+
+print("Default tools:", default_tools)
+```
+
+In both cases, the `mongodb_toolbox` decorator is used to register functions, and the `populate_tools` method is used to retrieve relevant tools based on a user query. The main difference is in the setup and configuration.
+
+The custom configuration approach allows you to specify your own MongoDB URI, database name, collection name, and other settings. This is useful when you need to connect to a specific MongoDB instance or customize the behavior of the tools.
+
+The default configuration approach is simpler and requires less setup. It's suitable for quick starts or when the default settings meet your needs.
+
+Choose the approach that best fits your project requirements and structure.
+
+## Features
+
+- MongoDB Tools:
+  - Automatic tool registration with MongoDB
+  - Vector search based on user queries
+  - Customizable number of tools returned
+  - Configurable embedding model and search parameters
+  - Error handling and logging
+- Extensible structure for future database support
+
+
+## Feature Roadmap
+
+- [x] Implement basic MongoDB tools functionality
+- [x] Add customizable vector search
+- [x] Implement error handling and logging
+- [x] Create PyPI package
+- [x] Restructure package for extensibility to other databases
+- [ ] Add support for multiple embedding models to make MongoDBToolsConfig embedding model agnostic
+- [ ] Implement MemScore logic for improved tool ranking and memory component retrival
+- [ ] Add async support for improved performance
+- [ ] Implement caching mechanism for embeddings and search results
+- [ ] Create comprehensive API documentation
+- [ ] Implement automated testing suite with high coverage
+- [ ] Create example projects and use cases
+- [ ] Add support for additional databases (e.g., PostgreSQL, Redis)
+
+## License
+
+This project is licensed under the MIT License.

memorizz-0.0.1/pyproject.toml

@@ -0,0 +1,25 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "memorizz"
+version = "0.0.1"
+authors = [
+  { name="Richmond Alake", email="richmond.alake@gmail.com" },
+]
+description = "A memory management library for Python"
+readme = "README.md"
+requires-python = ">=3.7"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[project.urls]
+"Homepage" = "https://github.com/RichmondAlake/memorizz"
+"Bug Tracker" = "https://github.com/yourusername/memorizz/issues"

memorizz-0.0.1/src/memorizz/__init__.py

@@ -0,0 +1,6 @@
+print("Starting memorizz __init__.py")
+from .database.mongodb import MongoDBTools, MongoDBToolsConfig, get_embedding, get_mongodb_toolbox
+print("Finished importing from mongodb in memorizz __init__.py")
+
+__all__ = ['MongoDBTools', 'MongoDBToolsConfig', 'get_embedding', 'get_mongodb_toolbox']
+print("Exiting memorizz __init__.py")

memorizz-0.0.1/src/memorizz/database/__init__.py

@@ -0,0 +1,5 @@
+print("Entering database __init__.py")
+from .mongodb import MongoDBTools, MongoDBToolsConfig, get_embedding, get_mongodb_toolbox
+
+__all__ = ['MongoDBTools', 'MongoDBToolsConfig', 'get_embedding', 'get_mongodb_toolbox']
+print("Exiting database __init__.py")

memorizz-0.0.1/src/memorizz/database/mongodb/__init__.py

@@ -0,0 +1,5 @@
+print("Entering mongodb __init__.py")
+from .mongodb_tools import MongoDBTools, MongoDBToolsConfig, get_embedding, get_mongodb_toolbox
+
+__all__ = ['MongoDBTools', 'MongoDBToolsConfig', 'get_embedding', 'get_mongodb_toolbox']
+print("Exiting mongodb __init__.py")

memorizz-0.0.1/src/memorizz/database/mongodb/mongodb_tools.py

@@ -0,0 +1,166 @@
+import os
+import json
+import getpass
+import inspect
+from functools import wraps
+from typing import get_type_hints, List, Dict, Any, Optional
+import openai
+import pymongo
+import logging
+from dataclasses import dataclass
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+@dataclass
+class MongoDBToolsConfig:
+    mongo_uri: Optional[str] = None
+    db_name: str = 'function_calling_db'
+    collection_name: str = 'tools'
+    embedding_model: str = "text-embedding-3-small"
+    vector_search_candidates: int = 150
+    vector_index_name: str = "vector_index"
+
+def get_embedding(text: str, model: str = "text-embedding-3-small") -> List[float]:
+    text = text.replace("\n", " ")
+    try:
+        return openai.OpenAI().embeddings.create(input=[text], model=model).data[0].embedding
+    except Exception as e:
+        logger.error(f"Error generating embedding: {str(e)}")
+        raise
+
+class MongoDBTools:
+    def __init__(self, config: MongoDBToolsConfig = MongoDBToolsConfig()):
+        self.config = config
+        if self.config.mongo_uri is None:
+            self.config.mongo_uri = os.getenv('MONGO_URI') or getpass.getpass("Enter MongoDB URI: ")
+        try:
+            self.mongo_client = pymongo.MongoClient(self.config.mongo_uri)
+            self.db = self.mongo_client[self.config.db_name]
+            self.tools_collection = self.db[self.config.collection_name]
+        except Exception as e:
+            logger.error(f"Error connecting to MongoDB: {str(e)}")
+            raise
+
+    def mongodb_toolbox(self, collection: Optional[pymongo.collection.Collection] = None):
+        if collection is None:
+            collection = self.tools_collection
+
+        def decorator(func):
+            @wraps(func)
+            def wrapper(*args, **kwargs):
+                return func(*args, **kwargs)
+
+            signature = inspect.signature(func)
+            docstring = inspect.getdoc(func) or ""
+
+            if not docstring:
+                raise ValueError(f"Error registering tool {func.__name__}: Docstring is missing. Please provide a docstring for the function.")
+
+            type_hints = get_type_hints(func)
+
+            tool_def = {
+                "name": func.__name__,
+                "description": docstring.strip(),
+                "parameters": {
+                    "type": "object",
+                    "properties": {},
+                    "required": []
+                }
+            }
+
+            for param_name, param in signature.parameters.items():
+                if param.kind in (inspect.Parameter.VAR_POSITIONAL, inspect.Parameter.VAR_KEYWORD):
+                    continue
+
+                param_type = type_hints.get(param_name, type(None))
+                json_type = "string"
+                if param_type in (int, float):
+                    json_type = "number"
+                elif param_type == bool:
+                    json_type = "boolean"
+
+                tool_def["parameters"]["properties"][param_name] = {
+                    "type": json_type,
+                    "description": f"Parameter {param_name}"
+                }
+
+                if param.default == inspect.Parameter.empty:
+                    tool_def["parameters"]["required"].append(param_name)
+
+            tool_def["parameters"]["additionalProperties"] = False
+
+            try:
+                vector = get_embedding(tool_def["description"], self.config.embedding_model)
+                tool_doc = {
+                    **tool_def,
+                    "embedding": vector
+                }
+                collection.update_one({"name": func.__name__}, {"$set": tool_doc}, upsert=True)
+                logger.info(f"Successfully registered tool: {func.__name__}")
+            except Exception as e:
+                logger.error(f"Error registering tool {func.__name__}: {str(e)}")
+                raise
+
+            return wrapper
+        return decorator
+
+    def _vector_search(self, user_query: str, collection: Optional[pymongo.collection.Collection] = None, limit: int = 2) -> List[Dict[str, Any]]:
+        if collection is None:
+            collection = self.tools_collection
+
+        try:
+            query_embedding = get_embedding(user_query, self.config.embedding_model)
+        except Exception as e:
+            logger.error(f"Error generating embedding for query: {str(e)}")
+            raise
+
+        vector_search_stage = {
+            "$vectorSearch": {
+                "index": self.config.vector_index_name,
+                "queryVector": query_embedding,
+                "path": "embedding",
+                "numCandidates": self.config.vector_search_candidates,
+                "limit": limit
+            }
+        }
+
+        unset_stage = {
+            "$unset": "embedding"
+        }
+
+        pipeline = [vector_search_stage, unset_stage]
+
+        try:
+            results = collection.aggregate(pipeline)
+            return list(results)
+        except Exception as e:
+            logger.error(f"Error performing vector search: {str(e)}")
+            raise
+
+    def populate_tools(self, user_query: str, num_tools: int = 2) -> List[Dict[str, Any]]:
+        try:
+            search_results = self._vector_search(user_query, limit=num_tools)
+            tools = []
+            for result in search_results:
+                print(result)
+                tool = {
+                    "type": "function",
+                    "function": {
+                        "name": result["name"],
+                        "description": result["description"],
+                        "parameters": result["parameters"]
+                    }
+                }
+                tools.append(tool)
+            logger.info(f"Successfully populated {len(tools)} tools")
+            return tools
+        except Exception as e:
+            logger.error(f"Error populating tools: {str(e)}")
+            raise
+
+__all__ = ['MongoDBTools', 'MongoDBToolsConfig', 'get_embedding']
+
+# You can create a function to get the mongodb_toolbox decorator:
+def get_mongodb_toolbox(config: MongoDBToolsConfig = MongoDBToolsConfig()):
+    return MongoDBTools(config).mongodb_toolbox

memorizz-0.0.1/test.ipynb

@@ -0,0 +1,265 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from memorizz.database.mongodb import mongodb_tools, MongoDBToolsConfig, MongoDBTools, get_mongodb_toolbox"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "OPENAI_API_KEY = getpass.getpass(\"OpenAI API Key: \")\n",
+    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY\n",
+    "\n",
+    "MONGO_URI = getpass.getpass(\"Enter MongoDB URI: \")\n",
+    "os.environ[\"MONGO_URI\"] = MONGO_URI\n",
+    "\n",
+    "GPT_MODEL = \"gpt-4o\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Option 1: Create MongoDBTools instance and get the decorator\n",
+    "config = MongoDBToolsConfig(mongo_uri=MONGO_URI)\n",
+    "mongodb_tools = MongoDBTools(config)\n",
+    "# mongodb_toolbox = mongodb_tools.mongodb_toolbox"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Option 2: Use the get_mongodb_toolbox function\n",
+    "mongodb_toolbox = get_mongodb_toolbox(config)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings \"HTTP/1.1 400 Bad Request\"\n",
+      "ERROR:memorizz.database.mongodb.mongodb_tools:Error generating embedding: Error code: 400 - {'error': {'message': \"'$.input' is invalid. Please check the API reference: https://platform.openai.com/docs/api-reference.\", 'type': 'invalid_request_error', 'param': None, 'code': None}}\n",
+      "ERROR:memorizz.database.mongodb.mongodb_tools:Error registering tool shout: Error code: 400 - {'error': {'message': \"'$.input' is invalid. Please check the API reference: https://platform.openai.com/docs/api-reference.\", 'type': 'invalid_request_error', 'param': None, 'code': None}}\n"
+     ]
+    },
+    {
+     "ename": "BadRequestError",
+     "evalue": "Error code: 400 - {'error': {'message': \"'$.input' is invalid. Please check the API reference: https://platform.openai.com/docs/api-reference.\", 'type': 'invalid_request_error', 'param': None, 'code': None}}",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mBadRequestError\u001b[0m                           Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[40], line 5\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mrandom\u001b[39;00m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mdatetime\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m datetime\n\u001b[1;32m      4\u001b[0m \u001b[38;5;129;43m@mongodb_toolbox\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m----> 5\u001b[0m \u001b[38;5;28;43;01mdef\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;21;43mshout\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mstatement\u001b[49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mstr\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[38;5;241;43m>\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43mstr\u001b[39;49m\u001b[43m:\u001b[49m\n\u001b[1;32m      6\u001b[0m \u001b[43m  \u001b[49m\u001b[38;5;28;43;01mreturn\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mstatement\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mupper\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m      8\u001b[0m \u001b[38;5;129m@mongodb_toolbox\u001b[39m()\n\u001b[1;32m      9\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget_weather\u001b[39m(location: \u001b[38;5;28mstr\u001b[39m, unit: \u001b[38;5;28mstr\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcelsius\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28mstr\u001b[39m:\n",
+      "File \u001b[0;32m~/miniconda3/envs/memorizz/lib/python3.9/site-packages/memorizz/database/mongodb/mongodb_tools.py:90\u001b[0m, in \u001b[0;36mMongoDBTools.mongodb_toolbox.<locals>.decorator\u001b[0;34m(func)\u001b[0m\n\u001b[1;32m     87\u001b[0m tool_def[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparameters\u001b[39m\u001b[38;5;124m\"\u001b[39m][\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124madditionalProperties\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m     89\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 90\u001b[0m     vector \u001b[38;5;241m=\u001b[39m \u001b[43mget_embedding\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtool_def\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdescription\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mconfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membedding_model\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     91\u001b[0m     tool_doc \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m     92\u001b[0m         \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mtool_def,\n\u001b[1;32m     93\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124membedding\u001b[39m\u001b[38;5;124m\"\u001b[39m: vector\n\u001b[1;32m     94\u001b[0m     }\n\u001b[1;32m     95\u001b[0m     collection\u001b[38;5;241m.\u001b[39mupdate_one({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: func\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m}, {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m$set\u001b[39m\u001b[38;5;124m\"\u001b[39m: tool_doc}, upsert\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n",
+      "File \u001b[0;32m~/miniconda3/envs/memorizz/lib/python3.9/site-packages/memorizz/database/mongodb/mongodb_tools.py:27\u001b[0m, in \u001b[0;36mget_embedding\u001b[0;34m(text, model)\u001b[0m\n\u001b[1;32m     25\u001b[0m text \u001b[38;5;241m=\u001b[39m text\u001b[38;5;241m.\u001b[39mreplace(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m     26\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 27\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mopenai\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mOpenAI\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43membeddings\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcreate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mdata[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39membedding\n\u001b[1;32m     28\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m     29\u001b[0m     logger\u001b[38;5;241m.\u001b[39merror(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mError generating embedding: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mstr\u001b[39m(e)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
+      "File \u001b[0;32m~/miniconda3/envs/memorizz/lib/python3.9/site-packages/openai/resources/embeddings.py:114\u001b[0m, in \u001b[0;36mEmbeddings.create\u001b[0;34m(self, input, model, dimensions, encoding_format, user, extra_headers, extra_query, extra_body, timeout)\u001b[0m\n\u001b[1;32m    108\u001b[0m         embedding\u001b[38;5;241m.\u001b[39membedding \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mfrombuffer(  \u001b[38;5;66;03m# type: ignore[no-untyped-call]\u001b[39;00m\n\u001b[1;32m    109\u001b[0m             base64\u001b[38;5;241m.\u001b[39mb64decode(data), dtype\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfloat32\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    110\u001b[0m         )\u001b[38;5;241m.\u001b[39mtolist()\n\u001b[1;32m    112\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m obj\n\u001b[0;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_post\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    115\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/embeddings\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    116\u001b[0m \u001b[43m    \u001b[49m\u001b[43mbody\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmaybe_transform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43membedding_create_params\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mEmbeddingCreateParams\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    117\u001b[0m \u001b[43m    \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmake_request_options\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    118\u001b[0m \u001b[43m        \u001b[49m\u001b[43mextra_headers\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_headers\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    119\u001b[0m \u001b[43m        \u001b[49m\u001b[43mextra_query\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_query\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    120\u001b[0m \u001b[43m        \u001b[49m\u001b[43mextra_body\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextra_body\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    121\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    122\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpost_parser\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparser\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    123\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    124\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mCreateEmbeddingResponse\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    125\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/memorizz/lib/python3.9/site-packages/openai/_base_client.py:1260\u001b[0m, in \u001b[0;36mSyncAPIClient.post\u001b[0;34m(self, path, cast_to, body, options, files, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1246\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mpost\u001b[39m(\n\u001b[1;32m   1247\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m   1248\u001b[0m     path: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1255\u001b[0m     stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m   1256\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[1;32m   1257\u001b[0m     opts \u001b[38;5;241m=\u001b[39m FinalRequestOptions\u001b[38;5;241m.\u001b[39mconstruct(\n\u001b[1;32m   1258\u001b[0m         method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpost\u001b[39m\u001b[38;5;124m\"\u001b[39m, url\u001b[38;5;241m=\u001b[39mpath, json_data\u001b[38;5;241m=\u001b[39mbody, files\u001b[38;5;241m=\u001b[39mto_httpx_files(files), \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39moptions\n\u001b[1;32m   1259\u001b[0m     )\n\u001b[0;32m-> 1260\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m cast(ResponseT, \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrequest\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mopts\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m)\u001b[49m)\n",
+      "File \u001b[0;32m~/miniconda3/envs/memorizz/lib/python3.9/site-packages/openai/_base_client.py:937\u001b[0m, in \u001b[0;36mSyncAPIClient.request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m    928\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrequest\u001b[39m(\n\u001b[1;32m    929\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    930\u001b[0m     cast_to: Type[ResponseT],\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    935\u001b[0m     stream_cls: \u001b[38;5;28mtype\u001b[39m[_StreamT] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[1;32m    936\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m ResponseT \u001b[38;5;241m|\u001b[39m _StreamT:\n\u001b[0;32m--> 937\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    938\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcast_to\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcast_to\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    939\u001b[0m \u001b[43m        \u001b[49m\u001b[43moptions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moptions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    940\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    941\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstream_cls\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstream_cls\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    942\u001b[0m \u001b[43m        \u001b[49m\u001b[43mremaining_retries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mremaining_retries\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    943\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/miniconda3/envs/memorizz/lib/python3.9/site-packages/openai/_base_client.py:1041\u001b[0m, in \u001b[0;36mSyncAPIClient._request\u001b[0;34m(self, cast_to, options, remaining_retries, stream, stream_cls)\u001b[0m\n\u001b[1;32m   1038\u001b[0m         err\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mread()\n\u001b[1;32m   1040\u001b[0m     log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRe-raising status error\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m-> 1041\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_status_error_from_response(err\u001b[38;5;241m.\u001b[39mresponse) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1043\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_process_response(\n\u001b[1;32m   1044\u001b[0m     cast_to\u001b[38;5;241m=\u001b[39mcast_to,\n\u001b[1;32m   1045\u001b[0m     options\u001b[38;5;241m=\u001b[39moptions,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1049\u001b[0m     retries_taken\u001b[38;5;241m=\u001b[39moptions\u001b[38;5;241m.\u001b[39mget_max_retries(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmax_retries) \u001b[38;5;241m-\u001b[39m retries,\n\u001b[1;32m   1050\u001b[0m )\n",
+      "\u001b[0;31mBadRequestError\u001b[0m: Error code: 400 - {'error': {'message': \"'$.input' is invalid. Please check the API reference: https://platform.openai.com/docs/api-reference.\", 'type': 'invalid_request_error', 'param': None, 'code': None}}"
+     ]
+    }
+   ],
+   "source": [
+    "import random\n",
+    "from datetime import datetime\n",
+    "\n",
+    "@mongodb_toolbox()\n",
+    "def shout(statement: str) -> str:\n",
+    "  \"\"\"\n",
+    "  Convert a statement to uppercase letters to emulate shouting. Use this when a user wants to emphasize something strongly or when they explicitly ask to 'shout' something..\n",
+    "\n",
+    "  \"\"\"\n",
+    "  return statement.upper()\n",
+    "\n",
+    "@mongodb_toolbox()\n",
+    "def get_weather(location: str, unit: str = \"celsius\") -> str:\n",
+    "    \"\"\"\n",
+    "    Get the current weather for a specified location.\n",
+    "    Use this when a user asks about the weather in a specific place.\n",
+    "\n",
+    "    :param location: The name of the city or location to get weather for.\n",
+    "    :param unit: The temperature unit, either 'celsius' or 'fahrenheit'. Defaults to 'celsius'.\n",
+    "    :return: A string describing the current weather.\n",
+    "    \"\"\"\n",
+    "    conditions = [\"sunny\", \"cloudy\", \"rainy\", \"snowy\"]\n",
+    "    temperature = random.randint(-10, 35)\n",
+    "\n",
+    "    if unit.lower() == \"fahrenheit\":\n",
+    "        temperature = (temperature * 9/5) + 32\n",
+    "\n",
+    "    condition = random.choice(conditions)\n",
+    "    return f\"The weather in {location} is currently {condition} with a temperature of {temperature}°{'C' if unit.lower() == 'celsius' else 'F'}.\"\n",
+    "\n",
+    "@mongodb_toolbox()\n",
+    "def get_stock_price(symbol: str) -> str:\n",
+    "    \"\"\"\n",
+    "    Get the current stock price for a given stock symbol.\n",
+    "    Use this when a user asks about the current price of a specific stock.\n",
+    "\n",
+    "    :param symbol: The stock symbol to look up (e.g., 'AAPL' for Apple Inc.).\n",
+    "    :return: A string with the current stock price.\n",
+    "    \"\"\"\n",
+    "    price = round(random.uniform(10, 1000), 2)\n",
+    "    return f\"The current stock price of {symbol} is ${price}.\"\n",
+    "\n",
+    "@mongodb_toolbox()\n",
+    "def get_current_time(timezone: str = \"UTC\") -> str:\n",
+    "    \"\"\"\n",
+    "    Get the current time for a specified timezone.\n",
+    "    Use this when a user asks about the current time in a specific timezone.\n",
+    "\n",
+    "    :param timezone: The timezone to get the current time for. Defaults to 'UTC'.\n",
+    "    :return: A string with the current time in the specified timezone.\n",
+    "    \"\"\"\n",
+    "    current_time = datetime.utcnow().strftime(\"%H:%M:%S\")\n",
+    "    return f\"The current time in {timezone} is {current_time}.\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def populate_tools(search_results):\n",
+    "  \"\"\"\n",
+    "  Populate the tools array based on the results from the vector search.\n",
+    "\n",
+    "  Args:\n",
+    "  search_results (list): The list of documents returned from the vector search.\n",
+    "\n",
+    "  Returns:\n",
+    "  list: A list of tool definitions in the format required by the OpenAI API.\n",
+    "  \"\"\"\n",
+    "  tools = []\n",
+    "  for result in search_results:\n",
+    "    tool = {\n",
+    "      \"type\": \"function\",\n",
+    "      \"function\": {\n",
+    "        \"name\": result[\"name\"],\n",
+    "        \"description\": result[\"description\"],\n",
+    "        \"parameters\": result[\"parameters\"]\n",
+    "      }\n",
+    "    }\n",
+    "    tools.append(tool)\n",
+    "  return tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "user_query = \"Hi, can you shout the statement: We are there\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings \"HTTP/1.1 200 OK\"\n",
+      "INFO:memorizz.database.mongodb.mongodb_tools:Successfully populated 2 tools\n"
+     ]
+    }
+   ],
+   "source": [
+    "tools = mongodb_tools.populate_tools(user_query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[{'function': {'description': 'Convert a statement to uppercase letters to '\n",
+      "                              'emulate shouting. Use this when a user wants to '\n",
+      "                              'emphasize something strongly or when they '\n",
+      "                              \"explicitly ask to 'shout' something..\",\n",
+      "               'name': 'shout',\n",
+      "               'parameters': {'additionalProperties': False,\n",
+      "                              'properties': {'statement': {'description': 'Parameter '\n",
+      "                                                                          'statement',\n",
+      "                                                           'type': 'string'}},\n",
+      "                              'required': ['statement'],\n",
+      "                              'type': 'object'}},\n",
+      "  'type': 'function'},\n",
+      " {'function': {'description': 'Get the current stock price for a given stock '\n",
+      "                              'symbol.\\n'\n",
+      "                              'Use this when a user asks about the current '\n",
+      "                              'price of a specific stock.\\n'\n",
+      "                              '\\n'\n",
+      "                              ':param symbol: The stock symbol to look up '\n",
+      "                              \"(e.g., 'AAPL' for Apple Inc.).\\n\"\n",
+      "                              ':return: A string with the current stock price.',\n",
+      "               'name': 'get_stock_price',\n",
+      "               'parameters': {'additionalProperties': False,\n",
+      "                              'properties': {'symbol': {'description': 'Parameter '\n",
+      "                                                                       'symbol',\n",
+      "                                                        'type': 'string'}},\n",
+      "                              'required': ['symbol'],\n",
+      "                              'type': 'object'}},\n",
+      "  'type': 'function'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pprint\n",
+    "\n",
+    "pprint.pprint(tools)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "memorizz",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}