A NotebookLM companion for batch downloading NSE company announcements
Project description
KnowledgeLM
A CLI and web app to batch download NSE company announcements by category.
Intended as a companion for NotebookLM and other research tools.
Features
- CLI: Batch download filings with
knowledgelm download SYMBOL --from DATE --to DATE - Web UI: Streamlit app for interactive downloads
- Download announcements by category: Transcripts, Investor Presentations, Credit Ratings, Related Party Transactions, Annual Reports
- AI Agent Skill: Works with Claude Code, Gemini CLI, Codex, and other LLM agents
- NotebookLM Integration: Easily add downloaded files as sources to NotebookLM notebooks
Quick Start (CLI)
# Install
uv tool install knowledgelm
# Download all categories for a company
knowledgelm download HDFCBANK --from 2023-01-01 --to 2025-01-26
# Download specific categories
knowledgelm download INFY --from 2020-01-01 --to 2025-01-26 --categories transcripts,credit_rating
# List available categories
knowledgelm list-categories
# List downloaded files (for NotebookLM integration)
knowledgelm list-files ./HDFCBANK_knowledgeLM --json
AI Agent Skill Installation
KnowledgeLM includes an agent skill for use with Claude Code, Gemini CLI, Codex, or any LLM that supports the Agent Skills standard.
To install the skill, give this prompt to your AI agent:
Install the knowledgelm-nse skill by copying the
.agent/skills/knowledgelm-nse/directory (including all bundled resources) from the knowledgelm repository to your skills directory. The skill enables batch downloading of NSE India company filings and integration with NotebookLM.
The agent will locate the skill directory and install it to the appropriate location for your environment.
Web UI Usage
-
Run the Streamlit app:
streamlit run src/knowledgelm/app.py
-
Enter the company symbol, start date, and end date.
-
Choose the download folder.
-
Select download categories and/or which filings to display.
-
Click "Fetch Filings" to download.
Note on Credit Ratings: The app tries the primary source first (all available ratings). If unavailable, the fallback only fetches ratings within your date range.
Requirements
- Python 3.12+
- uv (recommended)
Using uv:
uv sync
Development
# Run tests
pytest
# Run with coverage
pytest --cov
# Format code
ruff format src/ tests/
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file knowledgelm-4.0.0.tar.gz.
File metadata
- Download URL: knowledgelm-4.0.0.tar.gz
- Upload date:
- Size: 116.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.26 {"installer":{"name":"uv","version":"0.9.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
99fcc81ca217f6cdb9e5e8b35460e45b548451cfb6490fa3ee772c92bf8257ea
|
|
| MD5 |
83a64f1022b15860fc0efc3f94f9170d
|
|
| BLAKE2b-256 |
1ca88717e83b760b307c1a46ae442f4376515a28f936f7e2d772caddfb632e31
|
File details
Details for the file knowledgelm-4.0.0-py3-none-any.whl.
File metadata
- Download URL: knowledgelm-4.0.0-py3-none-any.whl
- Upload date:
- Size: 30.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.26 {"installer":{"name":"uv","version":"0.9.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2319707ecf6b7e43955276bd5629b238a4e1554561c8a1bc8873d4395e6f2c38
|
|
| MD5 |
8d95096839915b41840758311dabd43b
|
|
| BLAKE2b-256 |
808fecf511d63d1f1799f65f8b35e82b2c0e228b34bc138d35660d1c733df89e
|
