pembot 0.1.0__py2.py3-none-any.whl → 0.1.2__py2.py3-none-any.whl

pembot/.git/COMMIT_EDITMSG

@@ -1 +1 @@
-fixed the type_info array pushing bug
+minor oopsie

pembot/.git/logs/HEAD

@@ -10,3 +10,6 @@ eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aea
 ef0503a60244391590b16042019032e91d7cc30d af80ddb5890f062e364ea8ade2d602df4e12de8c cyto <silverstone965@gmail.com> 1751896700 +0530	commit: added model name to convertor
 af80ddb5890f062e364ea8ade2d602df4e12de8c 0d28f73897db0c9a9351ee9e64d2a0fe27db2705 cyto <silverstone965@gmail.com> 1752081786 +0530	commit: upgraded to 0.0.8; added ability to classify the document chunks into one more filterable parameter 'type'; other query related improvements..
 0d28f73897db0c9a9351ee9e64d2a0fe27db2705 a898d2c3947d30d8be64bd2bbcef68f956d5456b cyto <silverstone965@gmail.com> 1752136060 +0530	commit: fixed the type_info array pushing bug
+a898d2c3947d30d8be64bd2bbcef68f956d5456b 784aa28d912b66e07748483efe0326c70d7541a5 cyto <silverstone965@gmail.com> 1752236415 +0530	commit: added prompt prefixing option to prime the llm with some more data; added the option for no-filter global search in a collection in search_within_document(s)
+784aa28d912b66e07748483efe0326c70d7541a5 f214d4d56726e2928479c5948bd88e038cf70b2e cyto <silverstone965@gmail.com> 1752858244 +0530	commit: added smolagent functionality with tool extension capability to query.py and added a caveat in search_within_documents by which you can just return no context if you set limit= 0, effectively doing a Non-contextual prompt
+f214d4d56726e2928479c5948bd88e038cf70b2e 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a cyto <silverstone965@gmail.com> 1752859643 +0530	commit: minor oopsie

pembot/.git/logs/refs/heads/main

@@ -10,3 +10,6 @@ eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aea
 ef0503a60244391590b16042019032e91d7cc30d af80ddb5890f062e364ea8ade2d602df4e12de8c cyto <silverstone965@gmail.com> 1751896700 +0530	commit: added model name to convertor
 af80ddb5890f062e364ea8ade2d602df4e12de8c 0d28f73897db0c9a9351ee9e64d2a0fe27db2705 cyto <silverstone965@gmail.com> 1752081786 +0530	commit: upgraded to 0.0.8; added ability to classify the document chunks into one more filterable parameter 'type'; other query related improvements..
 0d28f73897db0c9a9351ee9e64d2a0fe27db2705 a898d2c3947d30d8be64bd2bbcef68f956d5456b cyto <silverstone965@gmail.com> 1752136060 +0530	commit: fixed the type_info array pushing bug
+a898d2c3947d30d8be64bd2bbcef68f956d5456b 784aa28d912b66e07748483efe0326c70d7541a5 cyto <silverstone965@gmail.com> 1752236415 +0530	commit: added prompt prefixing option to prime the llm with some more data; added the option for no-filter global search in a collection in search_within_document(s)
+784aa28d912b66e07748483efe0326c70d7541a5 f214d4d56726e2928479c5948bd88e038cf70b2e cyto <silverstone965@gmail.com> 1752858244 +0530	commit: added smolagent functionality with tool extension capability to query.py and added a caveat in search_within_documents by which you can just return no context if you set limit= 0, effectively doing a Non-contextual prompt
+f214d4d56726e2928479c5948bd88e038cf70b2e 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a cyto <silverstone965@gmail.com> 1752859643 +0530	commit: minor oopsie

pembot/.git/logs/refs/remotes/origin/main

@@ -9,3 +9,6 @@ eb75e1c49f1e5b79dca17ccdbec8067756523238 0bdb4169fc0f312b8698f1df17a258fff163aea
 ef0503a60244391590b16042019032e91d7cc30d af80ddb5890f062e364ea8ade2d602df4e12de8c cyto <silverstone965@gmail.com> 1751896713 +0530	update by push
 af80ddb5890f062e364ea8ade2d602df4e12de8c 0d28f73897db0c9a9351ee9e64d2a0fe27db2705 cyto <silverstone965@gmail.com> 1752081801 +0530	update by push
 0d28f73897db0c9a9351ee9e64d2a0fe27db2705 a898d2c3947d30d8be64bd2bbcef68f956d5456b cyto <silverstone965@gmail.com> 1752136119 +0530	update by push
+a898d2c3947d30d8be64bd2bbcef68f956d5456b 784aa28d912b66e07748483efe0326c70d7541a5 cyto <silverstone965@gmail.com> 1752236436 +0530	update by push
+784aa28d912b66e07748483efe0326c70d7541a5 f214d4d56726e2928479c5948bd88e038cf70b2e cyto <silverstone965@gmail.com> 1752858280 +0530	update by push
+f214d4d56726e2928479c5948bd88e038cf70b2e 8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a cyto <silverstone965@gmail.com> 1752859659 +0530	update by push

pembot/.git/objects/78/4aa28d912b66e07748483efe0326c70d7541a5

@@ -0,0 +1 @@
+x
�PIn� �:��U�*P��7�r�$H�#��p�����+��~�m9�PaR��"��~vFe�5Z��"o�Z6�O=f�۱P���h7�Ɉ�M��)��qY,y����I!���n\�~W��#�*G�LF��5a�ϖ���I�A�c/��khX���#{��Vȇ��W��Ђ�%$��Ę�3�

pembot/.git/objects/e3/da98f3722c2d0c937db0872836fc4491e4487a

@@ -0,0 +1 @@
+x
e���0E��/]Xv7L؍i^�k��}J	oqqp���s�g

pembot/.git/refs/heads/main

@@ -1 +1 @@
-a898d2c3947d30d8be64bd2bbcef68f956d5456b
+8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a

pembot/.git/refs/remotes/origin/main

@@ -1 +1 @@
-a898d2c3947d30d8be64bd2bbcef68f956d5456b
+8fc00bf69f4ad3e50c13acc4a0988b6c0fe72b5a

pembot/TextEmbedder/mongodb_embedder.py

@@ -49,6 +49,9 @@ def search_within_document(
         A list of dictionaries, where each dictionary represents a matching chunk
         from the specified document, including its text, docId, and score.
     """
+    if limit < 1:
+        return []
+
     embeddings_collection = db_client[embeddings_collection_name]
 
     print(f"Searching within document (docId: {document_name_id})...")

pembot/__init__.py

@@ -1,6 +1,6 @@
 """
 A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 """
-__version__ = '0.1.0'
+__version__ = '0.1.2'
 from .main import save_to_json_file, make_query
 __all__ = ["save_to_json_file", "make_query"]

pembot/config/config.yaml

@@ -2,4 +2,4 @@ OUTPUT_DIR: /home/cyto/dev/pembotdir
 PAGE_DELIMITER: ___________________________ NEXT PAGE ___________________________
 app:
   name: pembot
-  version: 0.1.0
+  version: 0.1.2

pembot/pyrightconfig.json

@@ -0,0 +1,8 @@
+{
+  "venvPath": "..", // If your venv is a direct child like ./venv
+  "venv": "venvpem" // The name of your venv folder
+  // Or if you want to be explicit with the full path
+  // "pythonVersion": "3.9", // Or your specific version
+  // "pythonPlatform": "Linux", // Or "Windows", "Darwin"
+  // "pythonPath": "/path/to/your/project/.venv/bin/python" // Absolute path
+}

pembot/query.py

@@ -3,14 +3,34 @@ from huggingface_hub.inference._generated.types.chat_completion import ChatCompl
 from huggingface_hub.inference._providers import PROVIDER_T
 import ollama
 import re
+from smolagents import InferenceClientModel, ToolCallingAgent, ActionStep, TaskStep
+from smolagents.default_tools import VisitWebpageTool
+from pymongo import MongoClient
+from typing import Callable, Dict, Any, Optional, List
+import uuid
+from datetime import datetime
+from smolagents.monitoring import Timing
 
-from pydantic_core.core_schema import ErrorType
+
+from pembot.search import brave_search_tool
 from pembot.TextEmbedder.mongodb_embedder import search_within_document
 import numpy as np
 from huggingface_hub import InferenceClient
 from google import genai
 from google.genai import types
 import time
+from datetime import timezone
+
+init_timing= {
+    "start_time": 0.0,
+    "end_time": 0.0,
+    "duration": 0.0,
+}
+
+mongodb_uri= environ['MONGODB_SCHEMER']
+mc = MongoClient(mongodb_uri)
+db = mc["schemerdb"]
+collection = db["chat_history"]  # Collection name
 
 from pembot.TextEmbedder.mongodb_index_creator import create_vector_index
 
@@ -214,5 +234,263 @@ def remove_bs(text):
         return ""
 
 
+def smolquery(message: str, external_tools: list[Callable] = [], chat_id: str | None = None, allow_web_search= True) -> Dict[str, Any]:
+    """
+    Run agent with chat history support.
+
+    Args:
+        message: User's message
+        external_tools: List of external tools to use
+        chat_id: Optional chat ID for continuing conversation
+        allow_web_search: Boolean to decide whether to include brave tool to fetch search results
+                            and the Visiting Web Page Tool in the agent's toolbox
+
+    Returns:
+        Dictionary containing response and chat_id
+    """
+    alltools = []
+
+    if allow_web_search:
+        alltools.extend([
+            brave_search_tool,
+            VisitWebpageTool(),
+        ])
+
+    alltools.extend(external_tools)
+
+    model = InferenceClientModel(
+        token= environ["HF_TOKEN"],
+        # model_id= "HuggingFaceTB/SmolLM3-3B"
+        model_id= "deepseek-ai/DeepSeek-R1-0528"
+    )
+
+    agent = ToolCallingAgent(tools=alltools, model=model, add_base_tools=False)
+
+    # Handle chat history
+    if chat_id:
+        # Load existing conversation
+        chat_doc = collection.find_one({"_id": chat_id})
+        if chat_doc:
+            # Restore agent memory from database
+            restore_agent_memory(agent, chat_doc["messages"])
+        else:
+            # Chat ID provided but not found, create new one
+            chat_id = str(uuid.uuid4())
+    else:
+        # Create new chat
+        chat_id = str(uuid.uuid4())
+
+    # Run the agent
+    response = agent.run(message, reset= False)
+
+    # Extract the final answer from the response
+    final_answer = extract_final_answer(response)
+
+    # Save conversation to database
+    save_chat_history(chat_id, agent, message, final_answer)
+
+    return {
+        "response": final_answer,
+        "chat_id": chat_id
+    }
+
+def extract_final_answer(response: Any) -> str:
+    """
+    Extract the final answer from various response types.
+
+    Args:
+        response: Response from agent.run()
+
+    Returns:
+        Final answer as string
+    """
+    # Handle RunResult object
+    if hasattr(response, 'final_answer'):
+        return str(response.final_answer)
+
+    # Handle direct string response
+    if isinstance(response, str):
+        return response
+
+    # Handle generator response
+    if hasattr(response, '__iter__') and not isinstance(response, (str, bytes)):
+        final_step = None
+        for step in response:
+            final_step = step
+            # Look for FinalAnswerStep
+            if hasattr(step, 'final_answer'):
+                return str(step.final_answer)
+
+        # If no final answer found, return last step as string
+        if final_step is not None:
+            return str(final_step)
+
+    # Fallback to string conversion
+    return str(response)
+
+def restore_agent_memory(agent: ToolCallingAgent, messages: List[Dict[str, Any]]) -> None:
+    """
+    Restore agent memory from stored messages.
+
+    Args:
+        agent: The agent instance
+        messages: List of stored messages
+    """
+    for msg in messages:
+        if msg["type"] == "task":
+            # Add task step
+            task_step = TaskStep(
+                task=msg["content"],
+                task_images=msg.get("images", [])
+            )
+            agent.memory.steps.append(task_step)
+        elif msg["type"] == "action":
+            # Add action step with only the required parameters
+            # ActionStep objects are typically created during execution
+            # and contain read-only information, so we create a minimal one
+            action_saved_timing= msg.get("timing", init_timing)
+            action_step = ActionStep(
+                observations= msg.get("observations", ""),
+                step_number=msg["step_number"],
+                observations_images=msg.get("observations_images", []),
+                timing=Timing(
+                    start_time= action_saved_timing.get("start_time", 0.0),
+                    end_time= action_saved_timing.get("end_time", 0.0)
+                )
+            )
+            agent.memory.steps.append(action_step)
+
+def save_chat_history(chat_id: str, agent: ToolCallingAgent, user_message: str, agent_response: str) -> None:
+    """
+    Save conversation history to MongoDB.
+
+    Args:
+        chat_id: Chat session ID
+        agent: Agent instance with memory
+        user_message: Latest user message
+        agent_response: Agent's response
+    """
+    # Convert agent memory to serializable format
+    messages = []
+
+    for step in agent.memory.steps:
+        if isinstance(step, TaskStep):
+            messages.append({
+                "type": "task",
+                "content": step.task,
+                "images": step.task_images if hasattr(step, 'task_images') else [],
+                "timestamp": datetime.now(timezone.utc)
+            })
+        elif isinstance(step, ActionStep):
+            msg = {
+                "type": "action",
+                "step_number": step.step_number,
+                "observations_images": step.observations_images if hasattr(step, 'observations_images') else [],
+                "timing": step.timing.dict() if hasattr(step, 'timing') else init_timing,
+                "timestamp": datetime.now(timezone.utc)
+            }
+
+            # Store any additional attributes that might be accessible
+            # Note: ActionStep attributes are typically read-only
+            if hasattr(step, 'observations') and step.observations:
+                msg["observations"] = str(step.observations)
+            if hasattr(step, 'error') and step.error:
+                msg["error"] = str(step.error)
+
+            messages.append(msg)
+
+    # Add the latest response
+    messages.append({
+        "type": "response",
+        "content": agent_response,
+        "timestamp": datetime.now(timezone.utc)
+    })
+
+    # Update or insert chat document
+    collection.update_one(
+        {"_id": chat_id},
+        {
+            "$set": {
+                "messages": messages,
+                "last_updated": datetime.now(timezone.utc)
+            }
+        },
+        upsert=True
+    )
+
+def get_chat_history(chat_id: str) -> Optional[List[Dict[str, Any]]]:
+    """
+    Retrieve chat history by ID.
+
+    Args:
+        chat_id: Chat session ID
+
+    Returns:
+        List of messages or None if not found
+    """
+    chat_doc = collection.find_one({"_id": chat_id})
+    return chat_doc["messages"] if chat_doc else None
+
+def delete_chat_history(chat_id: str) -> bool:
+    """
+    Delete chat history by ID.
+
+    Args:
+        chat_id: Chat session ID
+
+    Returns:
+        True if deleted, False if not found
+    """
+    result = collection.delete_one({"_id": chat_id})
+    return result.deleted_count > 0
+
+def list_chat_sessions() -> List[Dict[str, Any]]:
+    """
+    List all chat sessions with basic info.
+
+    Returns:
+        List of chat sessions with ID and last updated time
+    """
+    sessions = []
+    for doc in collection.find({}, {"_id": 1, "last_updated": 1, "messages": {"$slice": 1}}):
+        first_message = doc["messages"][0] if doc["messages"] else {}
+        sessions.append({
+            "chat_id": doc["_id"],
+            "last_updated": doc.get("last_updated"),
+            "first_message": first_message.get("content", "")[:100] + "..." if len(first_message.get("content", "")) > 100 else first_message.get("content", "")
+        })
+    return sessions
+
+
+# # First message - creates new chat
+# result1 = smolquery("Hello, what's the weather like?", [])
+# print(f"Response: {result1['response']}")
+# print(f"Chat ID: {result1['chat_id']}")
+
+# # Second message - continues the conversation
+# result2 = smolquery("Thanks, now tell me about Python programming", [], chat_id=result1['chat_id'])
+# print(f"Response: {result2['response']}")
+# print(f"Chat ID: {result2['chat_id']}")  # Should be the same as result1['chat_id']
+
+# # Retrieve chat history
+# history = get_chat_history(result1['chat_id'])
+# print(f"Chat history length: {len(history) if history else 0}")
+
+
+
 if __name__ == "__main__":
     print("hemlo worls")
+
+    # result1 = smolquery("Did i tell you to do something regarding stocks before? What do you conclude?", allow_web_search= False, chat_id= "a52ab59e-d6d0-4089-a963-61e8876244e0")
+    result1 = smolquery("How has NIFTY 50 been doing past 3 months?")
+    print(f"Response: {result1['response']}")
+    print(f"Chat ID: {result1['chat_id']}")
+
+    # # Second message - continues the conversation
+    result2 = smolquery("now tell me about other indices in the same country", chat_id=result1['chat_id'])
+    print(f"Response: {result2['response']}")
+    print(f"Chat ID: {result2['chat_id']}")  # Should be the same as result1['chat_id']
+
+    # # Retrieve chat history
+    history = get_chat_history(result1['chat_id'])
+    print(f"Chat history length: {len(history) if history else 0}")

pembot/requirements.txt

@@ -2,6 +2,7 @@ aiofiles==24.1.0
 annotated-types==0.7.0
 anyio==4.9.0
 audioop-lts==0.2.1
+beautifulsoup4==4.13.4
 cachetools==5.5.2
 certifi==2025.6.15
 cffi==1.17.1
@@ -9,6 +10,7 @@ charset-normalizer==3.4.2
 click==8.2.1
 cryptography==45.0.5
 dnspython==2.7.0
+duckduckgo_search==8.1.1
 et_xmlfile==2.0.0
 fastapi==0.115.14
 ffmpy==0.6.0
@@ -27,7 +29,9 @@ httpx==0.28.1
 huggingface-hub==0.33.2
 idna==3.10
 Jinja2==3.1.6
+lxml==6.0.0
 markdown-it-py==3.0.0
+markdownify==1.1.0
 MarkupSafe==3.0.2
 mdurl==0.1.2
 msgpack==1.1.1
@@ -40,8 +44,9 @@ pandas==2.3.0
 pathlib==1.0.1
 pdfminer.six==20250506
 pdfplumber==0.11.7
-pembot==0.0.8
+pembot==0.1.2
 pillow==11.3.0
+primp==0.15.0
 pyasn1==0.6.1
 pyasn1_modules==0.4.2
 pycparser==2.22
@@ -55,6 +60,7 @@ pynvim==0.5.2
 pypdfium2==4.30.1
 pytesseract==0.3.13
 python-dateutil==2.9.0.post0
+python-dotenv==1.1.1
 python-multipart==0.0.20
 pytz==2025.2
 PyYAML==6.0.2
@@ -66,7 +72,9 @@ safehttpx==0.1.6
 semantic-version==2.10.0
 shellingham==1.5.4
 six==1.17.0
+smolagents==1.20.0
 sniffio==1.3.1
+soupsieve==2.7
 starlette==0.46.2
 tenacity==8.5.0
 tomlkit==0.13.3

pembot/search.py

@@ -0,0 +1,190 @@
+import os
+import requests
+import json
+from bs4 import BeautifulSoup
+from concurrent.futures import ThreadPoolExecutor, as_completed
+import logging
+from smolagents import tool
+
+# Configure logging for better visibility
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+def _fetch_and_extract_text(url: str, timeout: int = 10) -> dict:
+    """
+    Fetches the content of a URL and extracts all visible text (excluding HTML/CSS).
+
+    Args:
+        url (str): The URL to fetch.
+        timeout (int): Timeout in seconds for the HTTP request.
+
+    Returns:
+        dict: A dictionary containing the URL and its extracted text, or an error.
+    """
+    try:
+        logging.info(f"Attempting to fetch and parse URL: {url}")
+        response = requests.get(url, timeout=timeout)
+        response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx)
+
+        soup = BeautifulSoup(response.text, 'html.parser')
+
+        # Remove script and style tags
+        for script_or_style in soup(['script', 'style']):
+            script_or_style.extract()
+
+        # Get text, strip whitespace, and handle line breaks
+        text = soup.get_text(separator='\n', strip=True)
+
+        return {
+            "url": url,
+            "extracted_text": text
+        }
+    except requests.exceptions.Timeout:
+        logging.warning(f"Timeout fetching URL: {url}")
+        return {"url": url, "error": f"Timeout after {timeout} seconds"}
+    except requests.exceptions.RequestException as e:
+        logging.error(f"Error fetching URL {url}: {e}")
+        return {"url": url, "error": f"Failed to fetch: {e}"}
+    except Exception as e:
+        logging.error(f"An unexpected error occurred while parsing {url}: {e}")
+        return {"url": url, "error": f"Error parsing content: {e}"}
+
+
+@tool
+def brave_search_tool(query: str, num_results: int = 5, fetch_full_text: bool = False, full_text_timeout: int = 10) -> str:
+    """
+    Performs a web search using the Brave Search API and returns the results.
+    Optionally fetches and extracts text from the top search results.
+
+    Args:
+        query (str): The search query.
+        num_results (int): The maximum number of search results to return from Brave Search.
+                           Defaults to 5.
+        fetch_full_text (bool): If True, attempts to fetch and extract text from the URLs
+                                of the top results. Defaults to False.
+        full_text_timeout (int): Timeout in seconds for fetching each full text.
+                                Defaults to 10 seconds.
+
+    Returns:
+        str: A JSON string of the search results, optionally including extracted text,
+             or an error message.
+             JSON output is of the form:
+             {"title", "url", "snippet", "full_text"}
+    """
+    api_key = os.getenv("BRAVE_API_KEY")
+    if not api_key:
+        return json.dumps({"error": "Brave Search API key not found. Please set the BRAVE_API_KEY environment variable."})
+
+    url = "https://api.search.brave.com/res/v1/web/search"
+    headers = {
+        "Accept": "application/json",
+        "X-Subscription-Token": api_key
+    }
+    params = {
+        "q": query,
+        "count": num_results,
+        "offset": 0,
+        "country": "us",
+        "search_lang": "en"
+    }
+
+    try:
+        logging.info(f"Initiating Brave Search for query: '{query}' with {num_results} results.")
+        response = requests.get(url, headers=headers, params=params, timeout=15) # Brave API call timeout
+        response.raise_for_status()
+
+        data = response.json()
+        raw_web_results = []
+        if 'web' in data and 'results' in data['web']:
+            raw_web_results = data['web']['results']
+        else:
+            logging.warning("No web results found in Brave Search response.")
+            return json.dumps({"error": "No web results found in Brave Search response.", "raw_response": data})
+
+        formatted_results = []
+        urls_to_fetch = []
+
+        for result in raw_web_results:
+            formatted_item = {
+                "title": result.get("title"),
+                "url": result.get("url"),
+                "snippet": result.get("description")
+            }
+            formatted_results.append(formatted_item)
+            if fetch_full_text and result.get("url"):
+                urls_to_fetch.append(result["url"])
+
+        if fetch_full_text and urls_to_fetch:
+            logging.info(f"Fetching full text for {len(urls_to_fetch)} URLs with {full_text_timeout}s timeout per URL.")
+            # Use ThreadPoolExecutor to fetch URLs concurrently for efficiency
+            with ThreadPoolExecutor(max_workers=min(len(urls_to_fetch), 5)) as executor: # Limit concurrent fetches
+                future_to_url = {executor.submit(_fetch_and_extract_text, url, full_text_timeout): url for url in urls_to_fetch}
+                for future in as_completed(future_to_url):
+                    url = future_to_url[future]
+                    try:
+                        extracted_data = future.result()
+                        # Find the corresponding result in formatted_results and add extracted text
+                        for item in formatted_results:
+                            if item["url"] == url:
+                                item["full_text"] = extracted_data.get("extracted_text")
+                                if "error" in extracted_data:
+                                    item["full_text_error"] = extracted_data["error"]
+                                break
+                    except Exception as exc:
+                        logging.error(f"URL {url} generated an exception during full text fetch: {exc}")
+                        for item in formatted_results:
+                            if item["url"] == url:
+                                item["full_text_error"] = f"Failed to get full text due to internal error: {exc}"
+                                break
+
+        return json.dumps(formatted_results, indent=2)
+
+    except requests.exceptions.HTTPError as http_err:
+        logging.error(f"HTTP error occurred during Brave Search: {http_err} - Status: {response.status_code}")
+        return json.dumps({"error": f"HTTP error occurred with Brave Search: {http_err}", "status_code": response.status_code, "response_text": response.text})
+    except requests.exceptions.ConnectionError as conn_err:
+        logging.error(f"Connection error occurred during Brave Search: {conn_err}")
+        return json.dumps({"error": f"Connection error occurred with Brave Search: {conn_err}"})
+    except requests.exceptions.Timeout as timeout_err:
+        logging.error(f"Timeout error occurred during Brave Search API call: {timeout_err}")
+        return json.dumps({"error": f"Timeout error occurred with Brave Search API: {timeout_err}"})
+    except requests.exceptions.RequestException as req_err:
+        logging.error(f"An unexpected request error occurred during Brave Search: {req_err}")
+        return json.dumps({"error": f"An unexpected request error occurred with Brave Search: {req_err}"})
+    except json.JSONDecodeError:
+        logging.error("Failed to decode JSON response from Brave Search API.")
+        return json.dumps({"error": "Failed to decode JSON response from Brave Search API."})
+    except Exception as e:
+        logging.error(f"An unexpected error occurred in brave_search_tool: {e}", exc_info=True)
+        return json.dumps({"error": f"An unexpected error occurred in brave_search_tool: {e}"})
+
+# Example usage (for testing the tool function independently)
+if __name__ == "__main__":
+    # For testing, you might temporarily set the API key here or ensure it's in your env
+    # os.environ["BRAVE_API_KEY"] = "YOUR_BRAVE_API_KEY" # REMOVE IN PRODUCTION
+    # If not set, the tool will return an error about missing key
+
+    print("--- Testing Brave Search Tool with Full Text Fetch ---")
+    search_query = "Impact of AI on job market latest research"
+
+    # Test 1: Basic search (no full text)
+    print("\n--- Test 1: Basic Search ---")
+    results_basic = brave_search_tool(search_query, num_results=2, fetch_full_text=False)
+    print(results_basic)
+
+    # Test 2: Search with full text fetching
+    print("\n--- Test 2: Search with Full Text Fetch (num_results=2, timeout=5s) ---")
+    results_full_text = brave_search_tool(search_query, num_results=2, fetch_full_text=True, full_text_timeout=5)
+    print(results_full_text)
+
+    print("\n--- Test 3: Search with Full Text Fetch (num_results=1, very short timeout) ---")
+    results_short_timeout = brave_search_tool("impact of climate change on agriculture", num_results=1, fetch_full_text=True, full_text_timeout=1)
+    print(results_short_timeout)
+
+    print("\n--- Testing with missing API Key (example of error handling) ---")
+    original_key = os.getenv("BRAVE_API_KEY")
+    if original_key:
+        del os.environ["BRAVE_API_KEY"] # Temporarily unset for test
+    missing_key_results = brave_search_tool("test")
+    print(missing_key_results)
+    if original_key:
+        os.environ["BRAVE_API_KEY"] = original_key # Restore for other parts of the script

{pembot-0.1.0.dist-info → pembot-0.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pembot
-Version: 0.1.0
+Version: 0.1.2
 Summary: A Python Package to convert PEM blog content to usseful information by leveraging LLMs
 Author-email: cyto <aryan_sidhwani@protonmail.com>
 License-Expression: MIT

{pembot-0.1.0.dist-info → pembot-0.1.2.dist-info}/RECORD

@@ -1,17 +1,19 @@
 pembot/.gitignore,sha256=_7FTsZokJ_pzEyyPjOsGw5x5Xx3gUBFaafs7UlPsv9E,98
 pembot/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pembot/__init__.py,sha256=oq-JydA8x2prvUKvfrjXWp-GeFLh_qZPesfmB4ad6HE,211
+pembot/__init__.py,sha256=JS8ONln7V9MIxi_JrRdEW9Kc9ygOmpCCRKEYC9TnTjA,211
 pembot/gartner.py,sha256=3ALknQ5mSXIimmwCa3JFDzB_EW2hHEcQO1T2odyBquk,5408
 pembot/main.py,sha256=lZLIV8XPonvNoY4LVS-5fct1y9URMXWoSGJUKMw3Yg8,9667
 pembot/output_structure_local.py,sha256=YfpHzfTNeLMSsB_CjAamha9D6Iz7E1IC-tW9xPCMWFc,3000
 pembot/pem.py,sha256=mv6iGcN1peSY7z2dtCQ_BKj31EFBNfczBhps_d-0XDo,6377
-pembot/query.py,sha256=0RBnLDBz8pctbsw9GA2UHG-uZPippKYjBBfBBKe2Oec,8705
-pembot/requirements.txt,sha256=vnjZ3uO4Dd8qPFDq1F2qGromJ5jrEBfBeiDwz7rKijk,1360
-pembot/.git/COMMIT_EDITMSG,sha256=iRLy0abINakd4FBRWJuD-QQ_WWbXZusnr_9e3wo4d90,38
+pembot/pyrightconfig.json,sha256=j2O2tc8Z-Zu7hEnhN9neoKk6-iLkAlp4qOmAxFyHB7Y,368
+pembot/query.py,sha256=zgfIJsSMDatFPl0Fw3MhK7fO8uBB0Yj4rxEAExqGyGA,18054
+pembot/requirements.txt,sha256=BGGuhM9oXJGN6oueIu3AYmBMUXeo-BoEQFJHHyO1BCc,1508
+pembot/search.py,sha256=IW0F8QjE-HSYP47v5P9EqfnzKgFEf5CGxeICtHDDrkE,9137
+pembot/.git/COMMIT_EDITMSG,sha256=pTsMiZ9dt9Of1JgR5858BXwxO8jn7P0MpLw0pJE7dqc,13
 pembot/.git/HEAD,sha256=KNJb-Cr0wOK3L1CVmyvrhZ4-YLljCl6MYD2tTdsrboA,21
 pembot/.git/config,sha256=ZFl9d2GyxirgRXRsv8iULIieKxwGC9P6SAjB_AmTkmQ,271
 pembot/.git/description,sha256=hatsFj1DoX6pz3eIMIvKFGbxsKjRzJLibpv2PaQGKu4,73
-pembot/.git/index,sha256=CdDhKv_jjjaFu1MNjZTrZZ4GF_av7KNYh750IqRkGWg,1814
+pembot/.git/index,sha256=70Iy37BW4GBRzaodLY4qm1hjjcBml0r1cdcFyNX_G_I,1974
 pembot/.git/packed-refs,sha256=7DECsr7q7vJ6Gw6a2gS3dE4v-YzbxGiWYoSWM43DgsQ,112
 pembot/.git/hooks/applypatch-msg.sample,sha256=AiNJeguLAzqlijpSG4YphpOGz3qw4vEBlj0yiqYhk_c,478
 pembot/.git/hooks/commit-msg.sample,sha256=H3TV6SkpebVz69WXQdRsuT_zkazdCD00C5Q3B1PZJDc,896
@@ -28,10 +30,10 @@ pembot/.git/hooks/push-to-checkout.sample,sha256=pT0HQXmLKHxt16-mSu5HPzBeZdP0lGO
 pembot/.git/hooks/sendemail-validate.sample,sha256=ROv8kj3FRmvACWAvDs8Ge5xlRZq_6IaN3Em3jmztepI,2308
 pembot/.git/hooks/update.sample,sha256=jV8vqD4QPPCLV-qmdSHfkZT0XL28s32lKtWGCXoU0QY,3650
 pembot/.git/info/exclude,sha256=ZnH-g7egfIky7okWTR8nk7IxgFjri5jcXAbuClo7DsE,240
-pembot/.git/logs/HEAD,sha256=TTHA6MsudjF1a9H4QECSP3XPvB-k2AOsA8mTVCEis_o,2980
-pembot/.git/logs/refs/heads/main,sha256=TTHA6MsudjF1a9H4QECSP3XPvB-k2AOsA8mTVCEis_o,2980
+pembot/.git/logs/HEAD,sha256=OrEUcE6427s9cKnTnrPMYZLrJcs4v-PSww3Zq_Tc060,3790
+pembot/.git/logs/refs/heads/main,sha256=OrEUcE6427s9cKnTnrPMYZLrJcs4v-PSww3Zq_Tc060,3790
 pembot/.git/logs/refs/remotes/origin/HEAD,sha256=OrkNquczPPh6fEGtutFKva_-_JhAdwnvXpCCPC4N6jk,194
-pembot/.git/logs/refs/remotes/origin/main,sha256=uxD0NKkje26omv-w0V09LJA81e-ccHAA-FY148tg93g,1606
+pembot/.git/logs/refs/remotes/origin/main,sha256=iJ6dB86rQ2-iqzRSdgRdjkze4t1IGz0MTxou3cwLYE4,2044
 pembot/.git/objects/01/5f71967c525963c827d7fe5415ae2c040c4a64,sha256=-qlT-5utWcwFnO3ADkH2SA2LBsdcph6wE2iePxJxkHs,170
 pembot/.git/objects/09/ee34d94dffd4c286df1d6d528b2e98e2a6cce2,sha256=FSXPGn6UBhR7s1Ug-afzCYLfGy8dE3Umn8dBKaahkDM,203
 pembot/.git/objects/0a/fb3a98cdc55b1434b44534ec2bf22c56cfa26c,sha256=Xxw20vI57zuhERWopDAZpQw6rAOhFtUr05lzpGyCTTE,120
@@ -39,6 +41,8 @@ pembot/.git/objects/0b/db4169fc0f312b8698f1df17a258fff163aeaa,sha256=hsOHhX0Yajg
 pembot/.git/objects/0c/8d9b2690545bf1906b05cd9f18b783b3eb74f1,sha256=GKt_CAJNOQXwGnoFLuiNpkd0s_hP_UDLKd59VRknYy0,330
 pembot/.git/objects/0c/ab66ffbaf50ef60dd41f3498595ebd2526b33c,sha256=Uk1dStvEBica-t38qHsZZ_4mxvi6b6VA9PaKE4KSunQ,90
 pembot/.git/objects/0d/28f73897db0c9a9351ee9e64d2a0fe27db2705,sha256=hqMFSXWo_05QL0Do-raB4AtK5QjvKLFBNc0RZqNga9o,244
+pembot/.git/objects/0e/120123bfadfd594220963f3bbca54056bab6ee,sha256=fj4c6vIKYMYSj5DEdXd6fcYGcanqaPGRD_9haJy35ns,56
+pembot/.git/objects/0f/ccea3d0db4864a854f8b2c13b9f76b3601d200,sha256=Fq6qF_9lqg1bYsF2tWArhzkldnfgLFELLK2CH_2XNcU,203
 pembot/.git/objects/10/9d1ca0463ea42bbbc435bcb43a90711211cf49,sha256=vR33_Raw-LpnaXGQc1MhSk_ZgEROO2Xa9n97YmA3gtQ,56
 pembot/.git/objects/14/22c2d0cf79fd928ff7e2d77f96ad5b40cc2a31,sha256=2INSnjkW4KTAcfO2aLYVzjnpT89NXxx8TBJj4iU9e3Y,170
 pembot/.git/objects/18/28e18ab80aa64d334b26428708140e280cbc63,sha256=PTF8WLVhzxBDTZhwU_PBHrkQBbijHbKvttSr0XVTOcU,3936
@@ -46,6 +50,7 @@ pembot/.git/objects/19/f61df7dbd562d04f561288677bbf2f18f5dff7,sha256=zg8IdUSnMYp
 pembot/.git/objects/1f/83a471c8119f7794d98c049170a5d7d07a4b71,sha256=XnMaYQUA8iT1fiOIvlBav331Ry7pNBOBqI3wB3Y1VM0,90
 pembot/.git/objects/28/db0ab48059acccd7d257aa02e52e9b6b83a4a5,sha256=S6PrWSQlkifYxKIgFdU0PZD0uLebS6uAP2LAUwp5yOI,91
 pembot/.git/objects/35/97e518a8658280be9f377f78edf1dfa1f23814,sha256=gfc5bFLVZpwNQb1Ox2VosDYAjw0Lc5ZLjmvNA8gWcmg,2546
+pembot/.git/objects/37/175696b3ca7a5d17379f03fb61a1023d50aeba,sha256=XaF3EsJ1wSIWtgBtgKsZkwiMK0NM8acFy9nnqE9_d0s,3085
 pembot/.git/objects/3d/07d3b29ff53d95de3898fb786d61732f210515,sha256=A9MNZO3QZ6ghGd1MyfmJ6H3dBTpF4HZcRosVxWytx8E,4077
 pembot/.git/objects/3d/e536f9c1fd05a23c2dec66423ed610afb0cf5f,sha256=omF4gmE9IQFZR8t6ybAKfnW02tdn9ZaVWKRhv_o1V4c,2083
 pembot/.git/objects/3e/23850624fcf5f111d6ea88ddd64adf924cf82f,sha256=ygVUpaLo7cxUdIgjFlaBh2BkllV6BIYYkzLIxsPKjWE,4111
@@ -56,23 +61,35 @@ pembot/.git/objects/41/ae8fa8f8baa2daee5ec0aa21ae17922ae051a0,sha256=TLuVmtSH9K3
 pembot/.git/objects/41/cbeb6bcb4c6fa9ef9be571082d95ecb4ea0ee3,sha256=waMrzjG_o5D4JgHkjjqcDQCwuS17w60JRkVr25ZFlcI,117
 pembot/.git/objects/42/f03e1b66aa56bbb36a1c3a8dea9e1e727faffa,sha256=n4W2gcagesjI1rStKNxQ98q5UOHlfwFJGUADFeYldoE,418
 pembot/.git/objects/44/86da0f89c566c3bae8abf435d37aeca87f1632,sha256=S2hY860Ep-0c7gQcbgrH6ioG7-Hw9a3BwYHcCkwy1Hg,3884
+pembot/.git/objects/44/9dea1ca63d6f1e47d119b36576acc94822a37c,sha256=gVL6GHxMRFhlOnyUCO1dSxnsBlMd4Jx90eNZFrv32UQ,6490
+pembot/.git/objects/4b/c4370a037feed828cca0915ebb0bb94b24a9d4,sha256=jt9lsSz8c3dw9PyfEEtkReCC_8YLXSKuc6ykSJCKZPM,487
 pembot/.git/objects/4d/a03134f70896f72053fbdc0cd4f4c76d4ac1d8,sha256=GBhAvxM1omIt-PN6mNXYlIJMN5nx2AUE0ZOf68El5pc,117
 pembot/.git/objects/50/39b29fda67743a044993436df6a4a1db7b8888,sha256=NYNmYtOq8IMmH32GaQSOBpTRTTm6jEJfY3vytVpzfKM,115
 pembot/.git/objects/51/9e780574933d7627a083222bd10dd74f430904,sha256=3e3Iu2-waVySghbLYXmwhDPpfhV4PF82suvjcYkSVog,3604
+pembot/.git/objects/59/69ac8b9d6b44a601385c3ed8c710a69d05216e,sha256=3IOcUn5myiozgeId1iWJZX-r7cS65xXnzQCEjrc-1ZA,168
+pembot/.git/objects/5c/4f01d3ce9e243bbb8a693f97e5c7d13a857cb7,sha256=BnHoA5JBo5NY2ReemhwmZ-dOdx6CwXWY1TQsc-FSM5o,242
 pembot/.git/objects/61/46a371b9c1bd9f51af273f11f986cfd1bedeba,sha256=KZvfnjxuriY54uWZQOM-GLovAvHs1k8_KwhpjNA5lW4,128
 pembot/.git/objects/63/1700a51c8fa97b543991f5f61bfcd1e7e1327d,sha256=sYkhBkrSPQ8klX2gPrXJUZVt2a0iaF7KC7NFGBuxgeY,4360
 pembot/.git/objects/64/00040794955d17c9a1fe1aaaea59f2c4822177,sha256=-tFnLFQvYrtkodOVhPK3WUhN8Qg9sQ8VfcEHG9MXdAg,421
 pembot/.git/objects/6d/7a865a23b1cb4182f67907820104ced48b11c9,sha256=dJRTCmT9rLygONcQ7MPETl9AImF3Iy5tB_KUeCvKyKY,2651
+pembot/.git/objects/71/014c7a6c8c98449a26ef966485a6cf30a1974d,sha256=ZamWua6G5BGjBYZYeG8dN3nHhwz_kqFfoYyO2wtuRV0,417
 pembot/.git/objects/72/f047cda92abcd1ddc857f6461de605f8668331,sha256=PFb9LUDMnUCnuJcXUa5W1ea__fdP17kNyWrnqvnOpjs,240
 pembot/.git/objects/73/2e98f08bc806c331b06847fc8c743f545499e5,sha256=kbKUb6fwwhRO73B4EZmol55JBvckqE3GNZ9PqHRB2ag,3995
+pembot/.git/objects/75/321fbcd2be44a548400fbacbf5bcb71e3810fd,sha256=7AXaYVgItbw3xQiEqeRyO5qdIedIxDoI9hTDn8CBRxM,56
+pembot/.git/objects/78/4aa28d912b66e07748483efe0326c70d7541a5,sha256=6ut1I6cMnpRs6EK2CZZv50W25yNc0Ha6nC_cj9tSQjI,249
 pembot/.git/objects/7a/7d28b0313a3d9d509823faaae31949af8610ef,sha256=X59k-p9VNLBpmJlL53qIz8mntLeCSpnjw-rq9u9z_6I,90
 pembot/.git/objects/7e/0907822f7d316ebe0be07e1f6918bef412c80b,sha256=lFc55Bu-vEXF8In553gHxlEsB47Vg2qFXHiJqepWEqg,5167
 pembot/.git/objects/86/cdaec229f1fbebf43042266b03878944669f25,sha256=eTvQhUeYXP8E181oTOcBydcgmImr62IizaH_Jbcbg8g,4077
 pembot/.git/objects/87/d6df5217a4a374f8c1211a05f9bd657f72c9a7,sha256=OGq5-x1lFa94vTX7WYO6o4TGvCZwAvZ6LXm6N3dpiKM,3881
 pembot/.git/objects/8b/5be2af9b16f290549193859c214cd9072212e8,sha256=DhGeGisCdFZ0TcRKp5angRpaseI87TQDt5FtGZInstk,117
+pembot/.git/objects/8d/adc1d7891c79de24ba2c7c38b4c830bf61870a,sha256=QJaAleJXlBhybaUcSeKB7nC9OJg9gjP_xc071Wyq8BM,115
+pembot/.git/objects/8f/c00bf69f4ad3e50c13acc4a0988b6c0fe72b5a,sha256=uJVaujaQWN_NwzK9P0SM7cYp3I6GQFXdlYBPrnqVhcg,159
 pembot/.git/objects/90/f067b86364ab243a7e3bc75f936319ba9eac88,sha256=FLAmmgvYuEAx1-ZBU30rvDzP0ppXWRSVrzPWVnArIb0,203
+pembot/.git/objects/93/652290aac46c69b1b4dd83062b6cfe648dd643,sha256=WPgmr5bXli5s8rNdiUQM4IB4o_xyJe6nuI3TG4e5aYs,487
 pembot/.git/objects/93/8f29d9b4b1ae86e39dddf9e3d115a82ddfc9b6,sha256=xf8oZ5IBMTxfkH7MFfukV7ZIu0Apd-78eJTdlI7GBv0,90
 pembot/.git/objects/95/28bbccd167e3f4ad583a1ae9fac98a52620e27,sha256=jwJdRviwjGJIyMpE_BM6mr7B9ofGEsI5ZToJo5nmlao,263
+pembot/.git/objects/97/b7aaa5c8b45f5471c9d39893cd4c893da6f444,sha256=PZW83V2jXf8-zDoTJqG1jNsCMURU8NUK8ljBD458MK0,3949
+pembot/.git/objects/99/89463f57f1f2931e5973bd543c80f18b0204bc,sha256=RoShFyJfmRnXYXP_y2c_e9KE_Otawr_T1mC22BqDNDI,6472
 pembot/.git/objects/9b/123713e30fc9e225f9ac8ff5b02f8f8cf86456,sha256=xIETiieOoilleucGg7vXOgjZ-v5PI0t34fDJjDD665A,4204
 pembot/.git/objects/a8/98d2c3947d30d8be64bd2bbcef68f956d5456b,sha256=lh2LurucwRdL6WP8ChgmjXrK2lR7HASIXzt4iHFrTf4,178
 pembot/.git/objects/a9/d5e349fa091647742b09eb3d05bac8f58fe547,sha256=kaU3Z4k6ptIwO8ktcjs2-kshb0bzM4y8Uur-a27_jnk,56
@@ -91,10 +108,12 @@ pembot/.git/objects/bf/32a7e6872e5dc4025ee3df3c921ec7ade0855f,sha256=lwL9ickzIFt
 pembot/.git/objects/bf/518686b06069d2a8abd3689908b7e1a6e16b05,sha256=w-HgdJdX2_ZdiIptJv8BcWdeDEyhl42WEk8P72X8YKU,421
 pembot/.git/objects/c0/793458db6e1bee7f79f1a504fb8ff4963f8ed3,sha256=b8lo_OrMeGgirc9yY_OFjv5xVpG6FBpZnBf7jbtlmyw,421
 pembot/.git/objects/c2/443060c07101948487cfa93cc39e082e9e0f5f,sha256=d9rjB8sgBOUQ-HQ8yu5I-c5Dqr_q2z0OOCXSufjDAak,3998
+pembot/.git/objects/c2/ce19d575a8cccf6886862c4fa6afefba142511,sha256=kxbbFUJ1TpEVIrqgiLzepP5Z1k_kF3FjCHvJ04yCBvs,3370
 pembot/.git/objects/ce/a4ffc1cf5eab61a2a0abd8f6dc941b580b69fd,sha256=yKUe_ZHD0UynTIrDRhuVqjDjKYDfZkWplqXjeSOD_bk,3894
 pembot/.git/objects/d0/937f7d832266337289d5ec09459f931a46fcf7,sha256=_RZ7Z2EZp1OOF_XZhY6e1tzWwhI8Fa5R9aaF_W8APBA,56
 pembot/.git/objects/e0/9162dbd64d85bb5ed740aa99faefa73f293d78,sha256=I5fpz3BQ2maFPTSu43T1uvYMuLiep1C3K6CsX8UMNPI,196
 pembot/.git/objects/e0/da740b542afc451c45b9b4be6c0c7a3c79b06c,sha256=oAb2b2VwhPXykdK_ZV8MEFwfy-ZPd2Nja2gAv20U7hc,115
+pembot/.git/objects/e3/da98f3722c2d0c937db0872836fc4491e4487a,sha256=DNdNDoMdjDexgwLErwUZDQCpvq4-QkFHtbVRXW_jKTk,168
 pembot/.git/objects/e5/3070f2b07f45d031444b09b1b38658f3caf29e,sha256=irJ-z8kPZmg85B0f4TQz73yJoCMWMWsIR3Pi5wx1Dlk,4034
 pembot/.git/objects/e7/911a702079a6144997ea4e70f59abbe59ec2bc,sha256=r4zY-__F4gSfjE7onRTrcxvv8umXKuPuFzd95AiQ0cs,392
 pembot/.git/objects/e9/1172752e9a421ae463112d2b0506b37498c98d,sha256=qWZpM65kQPSxlVHAtyzH5L-j3rL-b9Jw-A7YBm4NMlI,249
@@ -102,8 +121,11 @@ pembot/.git/objects/ea/0af89e61a882c5afc2a8c281b2d96f174bfe58,sha256=lXbMvL_xl8P
 pembot/.git/objects/eb/75e1c49f1e5b79dca17ccdbec8067756523238,sha256=ltEINFUpQP86CkE4nAT1Afegz3ytY3Nlx1P6ibTFEbo,305
 pembot/.git/objects/ee/a73c7f24094ed83b014f7cfce46e10f817bec8,sha256=fFYq_ODekFhF9SwBL9GP_fGDsNavXVVOuI6kmnHlkiY,5140
 pembot/.git/objects/ef/0503a60244391590b16042019032e91d7cc30d,sha256=mrF9jZHY2oJm8tkd8nQdMgUPbrZfENOFaR3mvbwi1dg,187
+pembot/.git/objects/ef/3488a3c636d73d82ad138e70a92453249b7f37,sha256=09VHFwSnSxOExWa3sKBzWAfSMyx5INI9KK2mstW8-xs,203
+pembot/.git/objects/f1/2d2ef8948cbe4b24279bee282f934cf5a1b834,sha256=HvfHm5CnbujMp-uu0aucVzpaWCy2aKBzaXknvlYCnjg,3937
 pembot/.git/objects/f1/3181b12cf4d539e635bf94ad6e950d68cedaf1,sha256=2cORujYAURTvGACujtNJvP1f-s7rt-UkrtPBuKfDR-g,419
 pembot/.git/objects/f1/655afa1c5636c8d58969e3194bb770aefbc552,sha256=Ugf-wTcOlwZXmxmbnjEc3iOK3dDRntTVONOJsrOjl3E,205
+pembot/.git/objects/f2/14d4d56726e2928479c5948bd88e038cf70b2e,sha256=e-Ff8_3sWUqd5ciQJLbXohN-E2ShUWKUiYZCHMitMus,290
 pembot/.git/objects/f4/e991088a63def67a30a2b8bbdb4d58514abab8,sha256=Y5WfCEpk121Cy9gaFfSY4ZkUz54qu45osRZdTy9kZ8c,393
 pembot/.git/objects/f6/b1d54483ce20fbcb252a8a93a5eff7bec88729,sha256=MrRy-fBSXZcp-yJM3e-tH3wCdUS-VFX6rW_mKTa-0_Y,419
 pembot/.git/objects/f8/6fbd490878cb0d3c35cc4443672d1309171bf1,sha256=hBVqthGLEEX2NmdD51kjiIeTd5CP5MU8it41zHlW3m0,419
@@ -114,20 +136,21 @@ pembot/.git/objects/fb/6c90c9ce5e0cdfbe074a3f060afc66f62eefde,sha256=Bmrnc27anjq
 pembot/.git/objects/fc/988aab7e2d46396dc595ad24345e8e77dda0e4,sha256=8982HA0S9bCm0JQsrgWzIkRNIiGfaDRUUrXsnuVjE6A,196
 pembot/.git/objects/fc/e56f1e09d09a05b9babf796fb40bece176f3a2,sha256=g-IVuI_8YBn048qkyyY6Vpn8zfP8UCJxUs0F5bDD6qM,1114
 pembot/.git/objects/fd/abd48f3e947a9f420003446dd118c5295346a5,sha256=cWWr70MLaXk82O6EIPpYlGUd5P30IUEELrbrh2MrUXE,115
+pembot/.git/objects/fe/cc5d8154b1e77e4c6beb23ce9cbe8fea55d34d,sha256=0it_Z3Lk5Mj06l0fJTVXs4RP4-kw_kFFJqFApwtKDfU,115
 pembot/.git/objects/pack/pack-d5469edc8c36e3bb1de5e0070e4d5b1eae935dd4.idx,sha256=CNzx_lz6v4PulPxRW2t9nz-ifvplpSFPhMA2M9WNUrA,3424
 pembot/.git/objects/pack/pack-d5469edc8c36e3bb1de5e0070e4d5b1eae935dd4.pack,sha256=dk3Sqrd0L-tNVLRy3uJdTYJNkw8v59mE1hV8zrCFNzc,41355
 pembot/.git/objects/pack/pack-d5469edc8c36e3bb1de5e0070e4d5b1eae935dd4.rev,sha256=7U3tpTWQ3dn5dwQo_KWMWxF31cKaDnCk2AzTO7Cx4Bg,388
-pembot/.git/refs/heads/main,sha256=UNQiShSvoG1AvbUvWeJLlN5V3ZHJSDarZ4vFLDI-Xh8,41
+pembot/.git/refs/heads/main,sha256=XQJQDbhwKcxH2eABZeHWgpv9Yedy7ytKBo0tRWo03ZM,41
 pembot/.git/refs/remotes/origin/HEAD,sha256=K7aiSqD8bEhBAPXVGim7rYQc0sdV9dk_qiBOXbtOsrQ,30
-pembot/.git/refs/remotes/origin/main,sha256=UNQiShSvoG1AvbUvWeJLlN5V3ZHJSDarZ4vFLDI-Xh8,41
+pembot/.git/refs/remotes/origin/main,sha256=XQJQDbhwKcxH2eABZeHWgpv9Yedy7ytKBo0tRWo03ZM,41
 pembot/AnyToText/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pembot/AnyToText/convertor.py,sha256=gqvhwFssUsAeirfO4n0Ztwga1hn8zHbdG96sMTjYrpE,17188
 pembot/TextEmbedder/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pembot/TextEmbedder/gemini_embedder.py,sha256=P679-2mmQESlYKML1vcrwx_-CSgWJgIQk7NL4F7BLQE,677
-pembot/TextEmbedder/mongodb_embedder.py,sha256=i5M56jaC2t3yUinqlXfC70GaTos4kSR_1LGsbljpEhU,10762
+pembot/TextEmbedder/mongodb_embedder.py,sha256=-xIr-zrAGzCmgNeojuX6qYj2t019EVO1I6g-Hwq0FL8,10799
 pembot/TextEmbedder/mongodb_index_creator.py,sha256=kopqdVYJii_wExVrXGZjMfqWZ2dD42b3PeNWo71weHI,5354
 pembot/TextEmbedder/vector_query.py,sha256=Kh1uhx9CatB-oQlQtnW-1I2Qz7MGHI20n2h_8peAChM,1986
-pembot/config/config.yaml,sha256=-6niASpCQzNynkHSTHWi3MawUWUHpOVuNg0Fhmun30M,156
+pembot/config/config.yaml,sha256=uLE_cngQbhDN3pwqRaZC60yhXP5dSFUYIWQKZ0qkhFM,156
 pembot/pdf2markdown/LICENSE,sha256=1JTJhQjUYDqJzFJhNtitm7mHyE71PRHgetIqRRWg6Pk,1068
 pembot/pdf2markdown/README.md,sha256=jitM1pwI69oa0N4mXv5-SY1ka9Sz3jsRNCDdpW-50kY,4545
 pembot/pdf2markdown/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -183,7 +206,7 @@ pembot/pdf2markdown/config/config.yaml,sha256=w75W2Eg4-tu8rRk_23PqxWDh0010kRKLmP
 pembot/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pembot/utils/inference_client.py,sha256=jeURmY2P5heVlH1dCV0XSgiX3U2qYGEmrnUv0KFpdww,5380
 pembot/utils/string_tools.py,sha256=gtRa5rBR0Q7GspTu2WtCnvhJQLFjPfWLvhmyiPkyStU,1883
-pembot-0.1.0.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pembot-0.1.0.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
-pembot-0.1.0.dist-info/METADATA,sha256=3tLhZEY9302ZgIQ2itAMbcM354jWyEcZ_Z3h2FeD1-8,313
-pembot-0.1.0.dist-info/RECORD,,
+pembot-0.1.2.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pembot-0.1.2.dist-info/WHEEL,sha256=Dyt6SBfaasWElUrURkknVFAZDHSTwxg3PaTza7RSbkY,100
+pembot-0.1.2.dist-info/METADATA,sha256=2Eaou5uE_IQB3jUmUnvxXuY_ifpKbo9ZhZpdVjj2DMk,313
+pembot-0.1.2.dist-info/RECORD,,