Merge pull request #55 from blink1073/INTPYTHON-442-lint

INTPYTHON-442 Add linting to repo

.pre-commit-config.yaml

@@ -16,7 +16,7 @@ repos:
   # Ruff version.
   rev: v0.8.2
   hooks:
-    # - id: ruff
-    #   args: ["--fix", "--show-fixes"]
     - id: ruff-format
       exclude: notebooks/techniques/evaluating_information_retrival_techniques_mongondb_langchain.ipynb
+    - id: ruff
+      args: ["--fix", "--show-fixes"]

notebooks/agents/MongoDB_Haystack_self_reflecting_Cooking_agent.ipynb

@@ -268,20 +268,19 @@
    },
    "outputs": [],
    "source": [
-    "from haystack import Pipeline, Document\n",
-    "from haystack.document_stores.types import DuplicatePolicy\n",
-    "from haystack.components.writers import DocumentWriter\n",
-    "from haystack.components.generators import OpenAIGenerator\n",
+    "from bson import json_util\n",
+    "from haystack import Document, Pipeline\n",
     "from haystack.components.builders.prompt_builder import PromptBuilder\n",
-    "from haystack.components.embedders import OpenAITextEmbedder, OpenAIDocumentEmbedder\n",
-    "from haystack_integrations.document_stores.mongodb_atlas import (\n",
-    "    MongoDBAtlasDocumentStore,\n",
-    ")\n",
+    "from haystack.components.embedders import OpenAIDocumentEmbedder, OpenAITextEmbedder\n",
+    "from haystack.components.generators import OpenAIGenerator\n",
+    "from haystack.components.writers import DocumentWriter\n",
+    "from haystack.document_stores.types import DuplicatePolicy\n",
     "from haystack_integrations.components.retrievers.mongodb_atlas import (\n",
     "    MongoDBAtlasEmbeddingRetriever,\n",
     ")\n",
-    "from datasets import load_dataset\n",
-    "from bson import json_util\n",
+    "from haystack_integrations.document_stores.mongodb_atlas import (\n",
+    "    MongoDBAtlasDocumentStore,\n",
+    ")\n",
     "\n",
     "dataset = {\n",
     "    \"train\": [\n",
@@ -1156,8 +1155,9 @@
    },
    "outputs": [],
    "source": [
-    "from colorama import Fore\n",
     "from typing import List\n",
+    "\n",
+    "from colorama import Fore\n",
     "from haystack import component\n",
     "\n",
     "\n",
@@ -1167,9 +1167,8 @@
     "    def run(self, replies: List[str]):\n",
     "        if \"DONE\" in replies[0]:\n",
     "            return {\"recipe\": replies[0].replace(\"done\", \"\")}\n",
-    "        else:\n",
-    "            print(Fore.RED + \"Not done yet, could make recipe more efficient\")\n",
-    "            return {\"recipe_to_check\": replies[0]}"
+    "        print(Fore.RED + \"Not done yet, could make recipe more efficient\")\n",
+    "        return {\"recipe_to_check\": replies[0]}"
    ]
   },
   {
@@ -1555,9 +1554,10 @@
     }
    ],
    "source": [
-    "from pymongo import MongoClient\n",
-    "import json\n",
     "import datetime\n",
+    "import json\n",
+    "\n",
+    "from pymongo import MongoClient\n",
     "\n",
     "query = \"How can I cook a lasagne?\"\n",
     "result = reflecting_rag_pipeline.run(\n",

notebooks/agents/agent_fireworks_ai_langchain_mongodb.ipynb

@@ -452,8 +452,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_openai import OpenAIEmbeddings\n",
     "from langchain_mongodb import MongoDBAtlasVectorSearch\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "embedding_model = OpenAIEmbeddings(model=\"text-embedding-3-small\", dimensions=256)\n",
     "\n",
@@ -556,8 +556,8 @@
    "outputs": [],
    "source": [
     "from langchain.agents import tool\n",
-    "from langchain_community.document_loaders import ArxivLoader\n",
     "from langchain.tools.retriever import create_retriever_tool\n",
+    "from langchain_community.document_loaders import ArxivLoader\n",
     "\n",
     "\n",
     "# Custom Tool Definiton\n",
@@ -727,8 +727,8 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_mongodb.chat_message_histories import MongoDBChatMessageHistory\n",
     "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain_mongodb.chat_message_histories import MongoDBChatMessageHistory\n",
     "\n",
     "\n",
     "def get_session_history(session_id: str) -> MongoDBChatMessageHistory:\n",

notebooks/agents/agentchat_RetrieveChat_mongodb.ipynb

@@ -54,10 +54,8 @@
     }
    ],
    "source": [
-    "import json\n",
     "import os\n",
     "\n",
-    "import autogen\n",
     "from autogen import AssistantAgent\n",
     "from autogen.agentchat.contrib.retrieve_user_proxy_agent import RetrieveUserProxyAgent\n",
     "\n",

notebooks/agents/agentic_rag_factory_safety_assistant_with_langgraph_langchain_mongodb.ipynb

@@ -35,8 +35,8 @@
    },
    "outputs": [],
    "source": [
-    "import os\n",
     "import getpass\n",
+    "import os\n",
     "\n",
     "\n",
     "# Function to securely get and set environment variables\n",
@@ -122,6 +122,7 @@
     "# Step 1: Data Loading\n",
     "import pandas as pd\n",
     "from datasets import load_dataset\n",
+    "\n",
     "# Make sure you have an Hugging Face token(HF_TOKEN) in your development environemnt before running the code below\n",
     "# How to get a token: https://huggingface.co/docs/hub/en/security-tokens\n",
     "\n",
@@ -961,9 +962,9 @@
     "                if isinstance(value, (pd.Series, np.ndarray, list)):\n",
     "                    # Handle array-like objects\n",
     "                    if len(value) > 0 and not pd.isna(value).all():\n",
-    "                        combined.append(f\"{attr.capitalize()}: {str(value)}\")\n",
+    "                        combined.append(f\"{attr.capitalize()}: {value!s}\")\n",
     "                elif not pd.isna(value):\n",
-    "                    combined.append(f\"{attr.capitalize()}: {str(value)}\")\n",
+    "                    combined.append(f\"{attr.capitalize()}: {value!s}\")\n",
     "        return \" \".join(combined)\n",
     "\n",
     "    df[\"combined_info\"] = df.apply(combine_row, axis=1)\n",
@@ -1056,8 +1057,8 @@
    "outputs": [],
    "source": [
     "import tiktoken\n",
-    "from tqdm import tqdm\n",
     "from langchain_openai import OpenAIEmbeddings\n",
+    "from tqdm import tqdm\n",
     "\n",
     "MAX_TOKENS = 8191  # Maximum tokens for text-embedding-3-small\n",
     "OVERLAP = 50\n",
@@ -1116,14 +1117,13 @@
     "    if isinstance(input_data, str):\n",
     "        # Return list of embeddings for string input\n",
     "        return chunk_embeddings[0]\n",
-    "    else:\n",
-    "        # Create duplicated rows for each chunk with the respective embedding for row input\n",
-    "        duplicated_rows = []\n",
-    "        for embedding in chunk_embeddings:\n",
-    "            new_row = input_data.copy()\n",
-    "            new_row[\"embedding\"] = embedding\n",
-    "            duplicated_rows.append(new_row)\n",
-    "        return duplicated_rows"
+    "    # Create duplicated rows for each chunk with the respective embedding for row input\n",
+    "    duplicated_rows = []\n",
+    "    for embedding in chunk_embeddings:\n",
+    "        new_row = input_data.copy()\n",
+    "        new_row[\"embedding\"] = embedding\n",
+    "        duplicated_rows.append(new_row)\n",
+    "    return duplicated_rows"
    ]
   },
   {
@@ -2029,8 +2029,7 @@
     "        # Connection successful\n",
     "        print(\"Connection to MongoDB successful\")\n",
     "        return client\n",
-    "    else:\n",
-    "        print(\"Connection to MongoDB failed\")\n",
+    "    print(\"Connection to MongoDB failed\")\n",
     "    return None\n",
     "\n",
     "\n",
@@ -2059,7 +2058,6 @@
    "outputs": [],
    "source": [
     "# Programmatically create vector search index for both colelctions\n",
-    "import time\n",
     "from pymongo.operations import SearchIndexModel\n",
     "\n",
     "\n",
@@ -2086,7 +2084,7 @@
     "        # time.sleep(20)  # Sleep for 20 seconds\n",
     "        print(f\"New index '{index_name}' created successfully:\", result)\n",
     "    except Exception as e:\n",
-    "        print(f\"Error creating new vector search index '{index_name}': {str(e)}\")"
+    "        print(f\"Error creating new vector search index '{index_name}': {e!s}\")"
    ]
   },
   {
@@ -2193,7 +2191,6 @@
    "outputs": [],
    "source": [
     "import pandas as pd\n",
-    "from pymongo import MongoClient\n",
     "from pymongo.errors import BulkWriteError\n",
     "\n",
     "\n",
@@ -2506,7 +2503,6 @@
    "outputs": [],
    "source": [
     "# Programatically create search indexes\n",
-    "from pymongo.operations import IndexModel\n",
     "\n",
     "\n",
     "def create_collection_search_index(collection, index_definition, index_name):\n",
@@ -2531,7 +2527,7 @@
     "        print(f\"Search index '{index_name}' created successfully\")\n",
     "        return result\n",
     "    except Exception as e:\n",
-    "        print(f\"Error creating search index: {str(e)}\")\n",
+    "        print(f\"Error creating search index: {e!s}\")\n",
     "        return None\n",
     "\n",
     "\n",
@@ -2642,9 +2638,9 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_openai import OpenAIEmbeddings\n",
     "from langchain_mongodb import MongoDBAtlasVectorSearch\n",
     "from langchain_mongodb.retrievers import MongoDBAtlasHybridSearchRetriever\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "ATLAS_VECTOR_SEARCH_INDEX = \"vector_index_with_filter\"\n",
     "embedding_model = OpenAIEmbeddings(\n",
@@ -2802,13 +2798,13 @@
    "outputs": [],
    "source": [
     "import pickle\n",
+    "from collections.abc import AsyncIterator\n",
     "from contextlib import AbstractContextManager\n",
+    "from datetime import datetime, timezone\n",
     "from types import TracebackType\n",
-    "from typing import Any, Dict, Optional, AsyncIterator, Union, List, Tuple\n",
+    "from typing import Any, Dict, List, Optional, Tuple, Union\n",
     "\n",
     "from langchain_core.runnables import RunnableConfig\n",
-    "from typing_extensions import Self\n",
-    "\n",
     "from langgraph.checkpoint.base import (\n",
     "    BaseCheckpointSaver,\n",
     "    Checkpoint,\n",
@@ -2818,7 +2814,7 @@
     ")\n",
     "from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer\n",
     "from motor.motor_asyncio import AsyncIOMotorClient\n",
-    "from datetime import datetime, timezone\n",
+    "from typing_extensions import Self\n",
     "\n",
     "\n",
     "class JsonPlusSerializerCompat(JsonPlusSerializer):\n",
@@ -3015,7 +3011,8 @@
    },
    "outputs": [],
    "source": [
-    "from typing import Dict, Any\n",
+    "from typing import Any, Dict\n",
+    "\n",
     "from langchain.agents import tool\n",
     "\n",
     "\n",
@@ -3099,9 +3096,9 @@
    },
    "outputs": [],
    "source": [
-    "from pydantic import BaseModel, Field, constr\n",
     "from typing import List\n",
-    "from datetime import datetime\n",
+    "\n",
+    "from pydantic import BaseModel, Field\n",
     "\n",
     "\n",
     "class Step(BaseModel):\n",
@@ -3144,7 +3141,7 @@
     "\n",
     "        return document\n",
     "    except Exception as e:\n",
-    "        raise ValueError(f\"Invalid safety procedure data: {str(e)}\")\n",
+    "        raise ValueError(f\"Invalid safety procedure data: {e!s}\")\n",
     "\n",
     "\n",
     "# Tool to add new safety procedures\n",
@@ -3323,9 +3320,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_openai import ChatOpenAI\n",
     "from langchain_anthropic import ChatAnthropic\n",
-    "from langchain_groq import ChatGroq\n",
     "\n",
     "# llm = ChatOpenAI(model=\"gpt-4o\", temperature=0)\n",
     "llm = ChatAnthropic(model=\"claude-3-sonnet-20240229\", temperature=0)\n",
@@ -3356,9 +3351,10 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
     "from datetime import datetime\n",
     "\n",
+    "from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "\n",
     "\n",
     "def create_agent(llm, tools, system_message: str):\n",
     "    \"\"\"Create an agent.\"\"\"\n",
@@ -3512,9 +3508,10 @@
    "outputs": [],
    "source": [
     "import operator\n",
-    "from langchain_core.messages import BaseMessage\n",
     "from typing import Annotated, TypedDict\n",
     "\n",
+    "from langchain_core.messages import BaseMessage\n",
+    "\n",
     "\n",
     "class AgentState(TypedDict):\n",
     "    messages: Annotated[List[BaseMessage], operator.add]\n",
@@ -3539,6 +3536,7 @@
    "outputs": [],
    "source": [
     "import functools\n",
+    "\n",
     "from langchain_core.messages import AIMessage, ToolMessage\n",
     "\n",
     "\n",
@@ -3676,8 +3674,8 @@
    "outputs": [],
    "source": [
     "import asyncio\n",
-    "from langchain_core.messages import HumanMessage, AIMessage\n",
-    "import time\n",
+    "\n",
+    "from langchain_core.messages import HumanMessage\n",
     "\n",
     "\n",
     "async def chat_loop():\n",
@@ -3704,7 +3702,7 @@
     "        for attempt in range(max_retries):\n",
     "            try:\n",
     "                async for chunk in graph.astream(state, config, stream_mode=\"values\"):\n",
-    "                    if \"messages\" in chunk and chunk[\"messages\"]:\n",
+    "                    if chunk.get(\"messages\"):\n",
     "                        last_message = chunk[\"messages\"][-1]\n",
     "                        if isinstance(last_message, AIMessage):\n",
     "                            last_message.name = (\n",
@@ -3719,12 +3717,12 @@
     "                break\n",
     "            except Exception as e:\n",
     "                if attempt < max_retries - 1:\n",
-    "                    print(f\"\\nAn unexpected error occurred: {str(e)}\")\n",
+    "                    print(f\"\\nAn unexpected error occurred: {e!s}\")\n",
     "                    print(f\"\\nRetrying in {retry_delay} seconds...\")\n",
     "                    await asyncio.sleep(retry_delay)\n",
     "                    retry_delay *= 2\n",
     "                else:\n",
-    "                    print(f\"\\nMax retries reached. OpenAI API error: {str(e)}\")\n",
+    "                    print(f\"\\nMax retries reached. OpenAI API error: {e!s}\")\n",
     "                    break\n",
     "\n",
     "        print(\"\\n\")  # New line after the complete response"