temporary fix to config cache

README.md

@@ -6,6 +6,8 @@ In a world dominated by Artificial Intelligence, having the ability to think
 
 Open Notebook empowers you to manage your research, generate AI-assisted notes, and interact with your content—on your terms.
 
+Learn more about our project at [https://www.open-notebook.ai](https://www.open-notebook.ai)
+
 ## ⚙️ Setting Up
 
 Go to the [Setup Guide](docs/SETUP.md) to learn how to set up the tool in details.

docs/TRANSFORMATIONS.md

@@ -31,28 +31,28 @@ source_insights:
   - name: "Summarize"
     insight_type: "Content Summary"
     description: "Summarize the content"
-    transformations:
+    patterns:
       - patterns/makeitdense
       - patterns/summarize
   - name: "Key Insights"
     insight_type: "Key Insights"
     description: "Extracts a list of the Key Insights of the content"
-    transformations:
+    patterns:
       - patterns/keyinsights
   - name: "Make it Dense"
     insight_type: "Dense Representation"
     description: "Create a dense representation of the content"
-    transformations:
+    patterns:
       - patterns/makeitdense
   - name: "Analyze Paper"
     insight_type: "Paper Analysis"
     description: "Analyze the paper and provide a quick summary"
-    transformations:
+    patterns:
       - patterns/analyze_paper
   - name: "Reflection"
     insight_type: "Reflection Questions"
     description: "Generates a list of insightful questions to provoke reflection"
-    transformations:
+    patterns:
       - patterns/reflection_questions
 ```
 

open_notebook/config.py

@@ -36,18 +36,20 @@ PODCASTS_FOLDER = f"{DATA_FOLDER}/podcasts"
 os.makedirs(PODCASTS_FOLDER, exist_ok=True)
 
 
-DEFAULT_MODELS = DefaultModels.load()
-
-if DEFAULT_MODELS.default_embedding_model:
-    EMBEDDING_MODEL = get_model(
-        DEFAULT_MODELS.default_embedding_model, model_type="embedding"
+def load_default_models():
+    default_models = DefaultModels.load()
+    embedding_model = (
+        get_model(default_models.default_embedding_model, model_type="embedding")
+        if default_models.default_embedding_model
+        else None
     )
-else:
-    EMBEDDING_MODEL = None
 
-if DEFAULT_MODELS.default_speech_to_text_model:
-    SPEECH_TO_TEXT_MODEL = get_model(
-        DEFAULT_MODELS.default_speech_to_text_model, model_type="speech_to_text"
+    speech_to_text_model = (
+        get_model(
+            default_models.default_speech_to_text_model, model_type="speech_to_text"
+        )
+        if default_models.default_speech_to_text_model
+        else None
     )
-else:
-    SPEECH_TO_TEXT_MODEL = None
+
+    return default_models, embedding_model, speech_to_text_model

open_notebook/domain/base.py

@@ -68,7 +68,9 @@ class ObjectModel(BaseModel):
         return None
 
     def save(self) -> None:
-        from open_notebook.config import EMBEDDING_MODEL
+        from open_notebook.config import load_default_models
+
+        DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
 
         try:
             logger.debug(f"Validating {self.__class__.__name__}")

open_notebook/domain/notebook.py

@@ -5,7 +5,7 @@ from langchain_core.runnables.config import RunnableConfig
 from loguru import logger
 from pydantic import BaseModel, Field, field_validator
 
-from open_notebook.config import EMBEDDING_MODEL
+from open_notebook.config import load_default_models
 from open_notebook.database.repository import (
     repo_create,
     repo_query,
@@ -140,6 +140,8 @@ class Source(ObjectModel):
             raise DatabaseOperationError(e)
 
     def vectorize(self) -> None:
+        DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
         try:
             if not self.full_text:
                 return
@@ -189,6 +191,8 @@ class Source(ObjectModel):
             raise DatabaseOperationError("Failed to search sources")
 
     def add_insight(self, insight_type: str, content: str) -> Any:
+        DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
         if not insight_type or not content:
             raise InvalidInputError("Insight type and content must be provided")
         try:
@@ -209,6 +213,8 @@ class Source(ObjectModel):
 
     # todo: move this to content processing pipeline as a major graph
     def generate_toc_and_title(self) -> "Source":
+        DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
         try:
             config = RunnableConfig(configurable=dict(thread_id=self.id))
             result = toc_graph.invoke({"content": self.full_text}, config=config)

open_notebook/graphs/chat.py

@@ -9,10 +9,12 @@ from langgraph.graph import END, START, StateGraph
 from langgraph.graph.message import add_messages
 from typing_extensions import TypedDict
 
-from open_notebook.config import DEFAULT_MODELS, LANGGRAPH_CHECKPOINT_FILE
+from open_notebook.config import LANGGRAPH_CHECKPOINT_FILE, load_default_models
 from open_notebook.domain.notebook import Notebook
 from open_notebook.graphs.utils import run_pattern
 
+DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
 
 class ThreadState(TypedDict):
     messages: Annotated[list, add_messages]

open_notebook/graphs/content_processing/audio.py

@@ -4,7 +4,7 @@ from math import ceil
 from loguru import logger
 from pydub import AudioSegment
 
-from open_notebook.config import SPEECH_TO_TEXT_MODEL
+from open_notebook.config import load_default_models
 from open_notebook.graphs.content_processing.state import SourceState
 
 # future: parallelize the transcription process
@@ -72,6 +72,8 @@ def split_audio(input_file, segment_length_minutes=15, output_prefix=None):
 
 
 def extract_audio(data: SourceState):
+    DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
     input_audio_path = data.get("file_path")
     audio_files = []
 

open_notebook/graphs/doc_query.py

@@ -1,14 +1,15 @@
-import os
-
 from langchain_core.runnables import (
     RunnableConfig,
 )
 from langgraph.graph import END, START, StateGraph
 from typing_extensions import TypedDict
 
+from open_notebook.config import load_default_models
 from open_notebook.domain.notebook import Note, Notebook, Source
 from open_notebook.graphs.utils import run_pattern
 
+DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
 
 class DocQueryState(TypedDict):
     doc_id: str
@@ -20,7 +21,7 @@ class DocQueryState(TypedDict):
 
 def call_model(state: dict, config: RunnableConfig) -> dict:
     model_id = config.get("configurable", {}).get(
-        "model_id", os.environ.get("RETRIEVAL_MODEL")
+        "model_id", DEFAULT_MODELS.default_transformation_model
     )
     return {"answer": run_pattern("doc_query", model_id, state)}
 

open_notebook/graphs/multipattern.py

@@ -7,9 +7,11 @@ from langchain_core.runnables import (
 from langgraph.graph import END, START, StateGraph
 from typing_extensions import Annotated, TypedDict
 
-from open_notebook.config import DEFAULT_MODELS
+from open_notebook.config import load_default_models
 from open_notebook.graphs.utils import run_pattern
 
+DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
 
 class PatternChainState(TypedDict):
     content_stack: Annotated[Sequence[str], operator.add]

open_notebook/graphs/pattern.py

@@ -4,9 +4,11 @@ from langchain_core.runnables import (
 from langgraph.graph import END, START, StateGraph
 from typing_extensions import TypedDict
 
-from open_notebook.config import DEFAULT_MODELS
+from open_notebook.config import load_default_models
 from open_notebook.graphs.utils import run_pattern
 
+DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
 
 class PatternState(TypedDict):
     input_text: str

open_notebook/graphs/recursive_toc.py

@@ -7,10 +7,12 @@ from langchain_core.runnables import (
 from langgraph.graph import END, START, StateGraph
 from typing_extensions import TypedDict
 
-from open_notebook.config import DEFAULT_MODELS
+from open_notebook.config import load_default_models
 from open_notebook.graphs.utils import run_pattern
 from open_notebook.utils import split_text
 
+DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
 
 class TocState(TypedDict):
     chunks: List[str]

open_notebook/graphs/summary.py

@@ -9,10 +9,12 @@ from langgraph.graph import END, START, StateGraph
 from pydantic import BaseModel
 from typing_extensions import TypedDict
 
-from open_notebook.config import DEFAULT_MODELS
+from open_notebook.config import load_default_models
 from open_notebook.graphs.utils import run_pattern
 from open_notebook.utils import split_text
 
+DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
 
 class SummaryResponse(BaseModel):
     """This is schema of your response. Please provide a JSON object with the enclosed keys"""

open_notebook/graphs/utils.py

@@ -1,7 +1,7 @@
 from langchain.output_parsers import OutputFixingParser
 from loguru import logger
 
-from open_notebook.config import DEFAULT_MODELS
+from open_notebook.config import load_default_models
 from open_notebook.models import get_model
 from open_notebook.prompter import Prompter
 from open_notebook.utils import token_count
@@ -18,7 +18,7 @@ def run_pattern(
     system_prompt = Prompter(prompt_template=pattern_name, parser=parser).render(
         data=state
     )
-
+    DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
     tokens = token_count(str(system_prompt) + str(messages))
 
     model_id = (

pages/2_📒_Notebooks.py

@@ -1,6 +1,7 @@
 import streamlit as st
 from humanize import naturaltime
 
+from open_notebook.config import load_default_models
 from open_notebook.domain.notebook import Notebook
 from stream_app.chat import chat_sidebar
 from stream_app.note import add_note, note_card
@@ -11,7 +12,6 @@ st.set_page_config(
     layout="wide", page_title="📒 Open Notebook", initial_sidebar_state="expanded"
 )
 
-
 version_sidebar()
 
 
@@ -71,6 +71,9 @@ def notebook_page(current_notebook_id):
     sources = current_notebook.sources
     notes = current_notebook.notes
 
+    # Load the default models dynamically
+    DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
     notebook_header(current_notebook)
 
     work_tab, chat_tab = st.columns([4, 2])
@@ -116,7 +119,6 @@ if st.session_state["current_notebook"]:
 st.title("📒 My Notebooks")
 st.caption("Here are all your notebooks")
 
-
 notebooks = Notebook.get_all(order_by="updated desc")
 
 for notebook in notebooks:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "open-notebook"
-version = "0.0.7"
+version = "0.0.8"
 description = "An open source implementation of a research assistant, inspired by Google Notebook LM"
 authors = ["Luis Novo <lfnovo@gmail.com>"]
 license = "MIT"

stream_app/source.py

@@ -7,7 +7,7 @@ import yaml
 from humanize import naturaltime
 from loguru import logger
 
-from open_notebook.config import UPLOADS_FOLDER
+from open_notebook.config import UPLOADS_FOLDER, load_default_models
 from open_notebook.domain.notebook import Asset, Source
 from open_notebook.exceptions import UnsupportedTypeException
 from open_notebook.graphs.content_processing import graph
@@ -16,6 +16,8 @@ from open_notebook.utils import surreal_clean
 
 from .consts import context_icons
 
+DEFAULT_MODELS, EMBEDDING_MODEL, SPEECH_TO_TEXT_MODEL = load_default_models()
+
 
 def run_patterns(input_text, patterns):
     output = transform_graph.invoke(dict(content_stack=[input_text], patterns=patterns))
@@ -162,7 +164,7 @@ def add_source(session_id):
                 st.stop()
 
             except Exception as e:
-                st.error(e)
+                st.exception(e)
                 return
 
         st.rerun()

transformations.yaml

@@ -31,5 +31,5 @@ source_insights:
   #   description: "Generates a list of insightful questions to provoke reflection"
   #   patterns:
   #     - patterns/default/reflection_questions
-  #     - patterns/default/translate
+  #     - patterns/user/translate