# Read Next
<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
## ReadNext: A Personal Papers Recommender
Every day, approximately 500 new papers are published in the `cs`
category on arXiv, with tens more in `cs.AI` alone. Amidst the recent
craze around Generative AI, I found it increasingly challenging to keep
up with the rapid influx of papers. Distilling the ones that were most
relevant to my work and my employer’s interests became a daunting task.
ReadNext was born out of these pressing needs:
- The necessity for a command-line tool, one that could be executed
directly or scheduled as a cron job.
- The requirement to access the latest papers from
[arXiv](https://arxiv.org).
- The integration with [Zotero](https://www.zotero.org), an excellent
tool for managing academic papers.
- The ability to propose a selection of `x` potentially relevant papers
based on my current research focus.
- The proposed papers should be accessible from the command line.
- The proposed papers should also be easily uploaded to Zotero.
The key focus is to recommend papers that align with my evolving
interests and research objectives, which may change on a daily basis and
need to be continuously accounted for.
## Install
You can easily install the ReadNext command line tool using `pip`:
``` sh
pip install readnext
```
## Requirements
ReadNext relies on one fundamental external services to create the
propose user workflow:
- `Zotero`: Zotero serves as the primary papers management tool, playing
a pivotal role in ReadNext’s workflow. To configure ReadNext on your
local computer, you have to create a Zotero account. If you do not
already have one, you will have to create one for yourself, please
refer to the section below.
By integrating Zotero, ReadNext helps in discovering papers that align
with your research interests and focus.
The second piece of the command line tool is the embedding system. That
system is used to create embeddings that are used to recommend papers to
users according to their current research focus. By default, ReadNext is
using the `BAAI/bge-base-en` [model from Hugging
Face](https://huggingface.co/BAAI/bge-base-en). Optionally, you can use
the Cohere embedding service instead. The processing is a little bit
faster depending on your local desktop, but it requires and additional
dependency.
Also note that the performance between the two systems are comparable.
In my experience, about 80% of the propositions are the same, and the
remaining 20% that are different yeld no major difference in accuracy.
However, I do prefer the `BAAI/bge-base-en` propositions a little
better.
### Zotero Account
If you do not have a Zotero account yet, you can [create one here for
free](https://www.zotero.org/user/register). This will give you a basic
account with `200MB` of space, sufficient to get started. Afterwards,
you can install the desktop application, mobile apps, and necessary
browser plugins to fully integrate Zotero into your digital environment.
Take the time to refer to [their extensive online
documentation](https://www.zotero.org/support/) to get to know its full
potential.
### Cohere Account (Optional)
For Cohere, you will have to [create an account and login on their
Dashboard](https://dashboard.cohere.ai/welcome/register). The services
are completely free for the volume and size of request required by
ReadNext.
## Configure
ReadNext currently needs to be configured using the environment
variables of your terminal session. The following configuration options
currently needs to be configured:
| Option | Description |
|----------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| COHERE_API_KEY | Cohere API Key as [created in their Dashboard here](https://dashboard.cohere.ai/api-keys) |
| ZOTERO_LIBRARY_ID | Your personal library ID as defined in Zotero’s backend. This [ID will appears here](https://www.zotero.org/settings/keys) as `Your userID for use in API calls is 750` |
| ZOTERO_LIBRARY_TYPE | Type of library: `user` or `group` |
| ZOTERO_API_KEY | You Zotero API Key, [it needs to be created and managed here](https://www.zotero.org/settings/keys). |
| CHROMA_DB_PATH | This is the local path where you want the embedding database management system to save its indexes (ex: `/Users/me/.readnext/chroma_db/`) |
| EMBEDDING_SYSTEM | This is the embedding system you want to use. One of: `BAAI/bge-base-en` (local) or `cohere`. |
| MODELS_PATH | This is the local path where you want the models files to be saved on your local file system (ex: `/Users/me/.readnext/models/`) |
| DOCS_PATH | This is the local path where you want the PDF files of the papers from arXiv to be saved locally (ex: `/Users/me/.readnext/docs/`) |
| RECOMMENDATIONS_PATH | This is the local path where you want the recommended papers to be saved locally (ex: `/Users/me/.readnext/recommendations/`) |
### Setup Environment Variables
#### For Windows
1. Open the Command Prompt or PowerShell.
2. Use the `setx` command to create a new environment variable
permanently. For example, to set the `ZOTERO_API_KEY`, you can use
the following command:
``` sh
setx ZOTERO_API_KEY "your_zotero_api_key_here"
```
The changes will take effect after you open a new command prompt or
restart your computer.
#### MacOS and Linux:
1. Open the Terminal.
2. Use the `export` command to set the environment variable for the
current session. For example, to set the `ZOTERO_API_KEY`, use the
following command:
``` sh
export ZOTERO_API_KEY="your_zotero_api_key_here"
```
This will set the `ZOTERO_API_KEY` variable for the current session
only.
To make the variable permanent, add the `export` command to your shell’s
configuration file. For example, if you’re using Bash, add the line to
the `~/.bashrc` or `~/.bash_profile` file. If you’re using Zsh, add it
to the `~/.zshrc` file. You can do this with a text editor or by using
the following command:
``` sh
echo 'export ZOTERO_API_KEY="your_zotero_api_key_here"' >> ~/.bashrc
```
Replace `~/.bashrc` with the appropriate file name if you’re using a
different shell configuration.
After saving the environment variables, they will be available in your
command line sessions, and any application that relies on them, such as
ReadNext, will be able to access the configured values. Remember to
restart your command line or open a new session after making changes to
ensure the environment variables take effect.
You can verify that the environment variables are set by running the
`env` command in your terminal session.
Here is what the full export looks like:
``` sh
export COHERE_API_KEY=""
export ZOTERO_LIBRARY_ID=""
export ZOTERO_API_KEY=""
export ZOTERO_LIBRARY_TYPE="user"
export EMBEDDING_SYSTEM="BAAI/bge-base-en"
export CHROMA_DB_PATH="/Users/[MY-USER/.readnext/chroma_db/"
export MODELS_PATH="/Users/[MY-USER]/.readnext/models/"
export DOCS_PATH="/Users/[MY-USER]/.readnext/docs/"
export RECOMMENDATIONS_PATH="/Users/[MY-USER]/.readnext/recommendations/"
```
## How it works?
ReadNext is a command line tool that can be used to generate
personalized paper recommendations based on your research interests. It
is designed to be used as a daily routine to help you discover new
papers that are relevant to your research focus.
The tool is designed to be used in conjunction with
[Zotero](https://www.zotero.org/), a free and open-source reference
management software to manage your research library. ReadNext will use
your Zotero library to identify your research interests and focus, and
will propose papers that are relevant to your research focus.
ReadNext is designed to be used as a daily routine. It will propose a
list of papers that are relevant to your research focus, and will save
them in a dedicated collection in your Zotero library. You can then
review the proposed papers and decide which ones you want to read. Once
you have read a paper, you can move it to another collection in your
Zotero library, and ReadNext will learn from your feedback to improve
the quality of the proposed papers.
ReadNext is designed to be used with with an embedding system. It uses
the system to generate embeddings for the papers in your Zotero library,
and will use these embeddings to identify papers that are similar to
your research focus. Two embedding systems are currently support: a
local one using the `BAAI/bge-base-en` model from Hugging Face, and a
remote one using the Cohere embedding service.
ReadNext is designed to be used with [arXiv](https://arxiv.org/), a free
service that provides access to scientific papers in the fields of
mathematics, physics, astronomy, computer science, quantitative biology,
statistics, and quantitative finance. ReadNext will use arXiv to
identify the latest papers in your research focus, and will propose them
to you as part of your daily routine.
The designed userflow is the following:
1. As a Zotero user, I will create one or multiple “Focus” collections
in my Zotero library. Those are the collections where I will add the
papers that are the most interesting to my current research. It is
expected that the content of those collections will change over time
as my research focus and interests evolves.
2. On a daily basis, I will run `readnext` in my terminal, or I will
create a cron job to run it automatically for me.
1. ReadNext will fetch the latest papers from arXiv
2. ReadNext will identify the papers that are relevant to your
research focus, as defined in Zotero
3. ReadNext will propose the relevant papers to me and add them to
Zotero in a dedicated collection where proposed papers are saved
3. I will go in Zotero, start to read the proposed papers, and if any
are of a particular interest I will add them to one of the “Focus”
collections
4. ReadNext will learn from your feedback to improve the quality of the
proposed papers
Now, let’s see how to actually do this.
## Usage
### Help
Any time, you can get contextual help for any command like this:
``` sh
readnext --help
```
``` sh
readnext personalized-papers --help
```
Those commands will tell you which arguments and options are available
for each command.
### arXiv categories and subcategories
You can get the full list of arXiv categories and subcategories by
running the following command:
``` sh
readnext arxiv-top-categories
```
``` sh
readnext arxiv-sub-categories
```
Those are the categories where you can get specific new papers from
arXiv.
### Getting new papers proposals
To get new papers proposals, you have to run the `personalized-papers`
command. That command requires two arguments:
- `category`: the arXiv top, or sub, category from which you want to get
new papers proposals
- `zotero_collection`: the name of the Zotero collection where your
papers of interest are stored in Zotero. This is what we refer to as
the “Focus” collection above. The name of the collection is case
sensitive and should be exactly as written in Zotero.
Then you also have three options available:
- `--proposals-collection`: which tells ReadNext that you want to save
the proposed papers in Zotero, in the Zotero Collection specified by
the argument. If you don’t use this option, ReadNext will only print
the proposed papers in the terminal, but will not save them in Zotero.
The default behaviour is that you don’t save them in Zotero.
- `--with-artifacts` / `-a`: which tells ReadNext that you want to save
the artifacts (PDF file of the papers and their summarization) into
Zotero. This is the recommended workflow, but it requires a lot more
space in your Zotero account. If you want to do this, you will most
likely need to subscribe to one of their paid option.
- `--nb-proposals`: which tells ReadNext how many papers you want to be
proposed. The default value is 10.
The following command will propose 3 papers from the `cs.AI` caterory,
based on the `Readnext-Focus-LLM` collection in my Zotero library, save
them in Zotero in the `Readnext-Propositions-LLM` with all related
artifacts:
``` sh
readnext personalized-papers cs.AI Readnext-Focus-LLM --proposals-collection=Readnext-Propositions-LLM --with-artifacts --nb-proposals=3
```
As you can see, you can easily create a series of topics you want papers
proposals around, where each of the topic is defined by a series of
specific papers that you read and found important for your research.
Here is what it looks like in the terminal:
Here is what it looks like in Zotero:
## Future Work
Here is a list of future work that could be done to improve ReadNext
after the initial release:
- **Adding an Abstraction Layer for Multiple Embedding Services**:
Currently, ReadNext utilizes Cohere for embeddings in its initial
version. LangChain could serve as a potential abstraction layer to
support multiple different embedding services.
- **Expanding Paper Sources with an Abstraction Layer**: ReadNext aims
to integrate additional paper sources beyond just arXiv. This will be
facilitated by implementing an abstraction layer for seamless
integration.
- **Enhancing Test Coverage**: To improve testing, we will go beyond
testing utility functions and incorporate mocks for external services,
ensuring comprehensive test coverage.
- **Interactive Configuration via Command Line Tool**: We plan to
augment the command line tool’s functionality, allowing users to
configure it directly from the command line using appropriate prompts
and interactions.
- **Refining Paper Selection Process**: Currently, every time readnext
is executed, it retrieves today’s latest papers from arXiv, identifies
relevant papers based on current interests, and matches them against
the personal research focus. To further enhance this functionality, we
may introduce additional capabilities, such as restricting proposed
papers to today’s papers only.
## Contributions
We welcome contributions to ReadNext! If you’d like to contribute,
please follow these steps:
1. Fork the repository on GitHub.
2. Create a new branch with a descriptive name:
`git checkout -b feature/your-feature-name`
3. Make your changes and commit them:
`git commit -m "Add feature: your feature name"`
4. Push your changes to your fork:
`git push origin feature/your-feature-name`
5. Submit a pull request to the `main` branch of the original
repository.
Raw data
{
"_id": null,
"home_page": "https://github.com/fgiasson/ReadNext",
"name": "readnext",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "nbdev jupyter notebook python",
"author": "Frederick Giasson",
"author_email": "Frederick Giasson <fred@fgiasson.com>",
"download_url": "https://files.pythonhosted.org/packages/a9/e1/f3a3b17c96c92b73484093a2c7fa291bfff40de4a27d9d0858fbb3375ae7/readnext-0.0.6.tar.gz",
"platform": null,
"description": "# Read Next\n\n<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->\n\n## ReadNext: A Personal Papers Recommender\n\nEvery day, approximately 500 new papers are published in the `cs`\ncategory on arXiv, with tens more in `cs.AI` alone. Amidst the recent\ncraze around Generative AI, I found it increasingly challenging to keep\nup with the rapid influx of papers. Distilling the ones that were most\nrelevant to my work and my employer\u2019s interests became a daunting task.\n\nReadNext was born out of these pressing needs:\n\n- The necessity for a command-line tool, one that could be executed\n directly or scheduled as a cron job.\n- The requirement to access the latest papers from\n [arXiv](https://arxiv.org).\n- The integration with [Zotero](https://www.zotero.org), an excellent\n tool for managing academic papers.\n- The ability to propose a selection of `x` potentially relevant papers\n based on my current research focus.\n- The proposed papers should be accessible from the command line.\n- The proposed papers should also be easily uploaded to Zotero.\n\nThe key focus is to recommend papers that align with my evolving\ninterests and research objectives, which may change on a daily basis and\nneed to be continuously accounted for.\n\n## Install\n\nYou can easily install the ReadNext command line tool using `pip`:\n\n``` sh\n pip install readnext\n```\n\n## Requirements\n\nReadNext relies on one fundamental external services to create the\npropose user workflow:\n\n- `Zotero`: Zotero serves as the primary papers management tool, playing\n a pivotal role in ReadNext\u2019s workflow. To configure ReadNext on your\n local computer, you have to create a Zotero account. If you do not\n already have one, you will have to create one for yourself, please\n refer to the section below.\n\nBy integrating Zotero, ReadNext helps in discovering papers that align\nwith your research interests and focus.\n\nThe second piece of the command line tool is the embedding system. That\nsystem is used to create embeddings that are used to recommend papers to\nusers according to their current research focus. By default, ReadNext is\nusing the `BAAI/bge-base-en` [model from Hugging\nFace](https://huggingface.co/BAAI/bge-base-en). Optionally, you can use\nthe Cohere embedding service instead. The processing is a little bit\nfaster depending on your local desktop, but it requires and additional\ndependency.\n\nAlso note that the performance between the two systems are comparable.\nIn my experience, about 80% of the propositions are the same, and the\nremaining 20% that are different yeld no major difference in accuracy.\nHowever, I do prefer the `BAAI/bge-base-en` propositions a little\nbetter.\n\n### Zotero Account\n\nIf you do not have a Zotero account yet, you can [create one here for\nfree](https://www.zotero.org/user/register). This will give you a basic\naccount with `200MB` of space, sufficient to get started. Afterwards,\nyou can install the desktop application, mobile apps, and necessary\nbrowser plugins to fully integrate Zotero into your digital environment.\n\nTake the time to refer to [their extensive online\ndocumentation](https://www.zotero.org/support/) to get to know its full\npotential.\n\n### Cohere Account (Optional)\n\nFor Cohere, you will have to [create an account and login on their\nDashboard](https://dashboard.cohere.ai/welcome/register). The services\nare completely free for the volume and size of request required by\nReadNext.\n\n## Configure\n\nReadNext currently needs to be configured using the environment\nvariables of your terminal session. The following configuration options\ncurrently needs to be configured:\n\n| Option | Description |\n|----------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| COHERE_API_KEY | Cohere API Key as [created in their Dashboard here](https://dashboard.cohere.ai/api-keys) |\n| ZOTERO_LIBRARY_ID | Your personal library ID as defined in Zotero\u2019s backend. This [ID will appears here](https://www.zotero.org/settings/keys) as `Your userID for use in API calls is 750` |\n| ZOTERO_LIBRARY_TYPE | Type of library: `user` or `group` |\n| ZOTERO_API_KEY | You Zotero API Key, [it needs to be created and managed here](https://www.zotero.org/settings/keys). |\n| CHROMA_DB_PATH | This is the local path where you want the embedding database management system to save its indexes (ex: `/Users/me/.readnext/chroma_db/`) |\n| EMBEDDING_SYSTEM | This is the embedding system you want to use. One of: `BAAI/bge-base-en` (local) or `cohere`. |\n| MODELS_PATH | This is the local path where you want the models files to be saved on your local file system (ex: `/Users/me/.readnext/models/`) |\n| DOCS_PATH | This is the local path where you want the PDF files of the papers from arXiv to be saved locally (ex: `/Users/me/.readnext/docs/`) |\n| RECOMMENDATIONS_PATH | This is the local path where you want the recommended papers to be saved locally (ex: `/Users/me/.readnext/recommendations/`) |\n\n### Setup Environment Variables\n\n#### For Windows\n\n1. Open the Command Prompt or PowerShell.\n2. Use the `setx` command to create a new environment variable\n permanently. For example, to set the `ZOTERO_API_KEY`, you can use\n the following command:\n\n``` sh\n setx ZOTERO_API_KEY \"your_zotero_api_key_here\"\n```\n\nThe changes will take effect after you open a new command prompt or\nrestart your computer.\n\n#### MacOS and Linux:\n\n1. Open the Terminal.\n2. Use the `export` command to set the environment variable for the\n current session. For example, to set the `ZOTERO_API_KEY`, use the\n following command:\n\n``` sh\nexport ZOTERO_API_KEY=\"your_zotero_api_key_here\"\n```\n\nThis will set the `ZOTERO_API_KEY` variable for the current session\nonly.\n\nTo make the variable permanent, add the `export` command to your shell\u2019s\nconfiguration file. For example, if you\u2019re using Bash, add the line to\nthe `~/.bashrc` or `~/.bash_profile` file. If you\u2019re using Zsh, add it\nto the `~/.zshrc` file. You can do this with a text editor or by using\nthe following command:\n\n``` sh\necho 'export ZOTERO_API_KEY=\"your_zotero_api_key_here\"' >> ~/.bashrc\n```\n\nReplace `~/.bashrc` with the appropriate file name if you\u2019re using a\ndifferent shell configuration.\n\nAfter saving the environment variables, they will be available in your\ncommand line sessions, and any application that relies on them, such as\nReadNext, will be able to access the configured values. Remember to\nrestart your command line or open a new session after making changes to\nensure the environment variables take effect.\n\nYou can verify that the environment variables are set by running the\n`env` command in your terminal session.\n\nHere is what the full export looks like:\n\n``` sh\nexport COHERE_API_KEY=\"\"\nexport ZOTERO_LIBRARY_ID=\"\"\nexport ZOTERO_API_KEY=\"\"\nexport ZOTERO_LIBRARY_TYPE=\"user\"\nexport EMBEDDING_SYSTEM=\"BAAI/bge-base-en\"\nexport CHROMA_DB_PATH=\"/Users/[MY-USER/.readnext/chroma_db/\"\nexport MODELS_PATH=\"/Users/[MY-USER]/.readnext/models/\"\nexport DOCS_PATH=\"/Users/[MY-USER]/.readnext/docs/\"\nexport RECOMMENDATIONS_PATH=\"/Users/[MY-USER]/.readnext/recommendations/\"\n```\n\n## How it works?\n\nReadNext is a command line tool that can be used to generate\npersonalized paper recommendations based on your research interests. It\nis designed to be used as a daily routine to help you discover new\npapers that are relevant to your research focus.\n\nThe tool is designed to be used in conjunction with\n[Zotero](https://www.zotero.org/), a free and open-source reference\nmanagement software to manage your research library. ReadNext will use\nyour Zotero library to identify your research interests and focus, and\nwill propose papers that are relevant to your research focus.\n\nReadNext is designed to be used as a daily routine. It will propose a\nlist of papers that are relevant to your research focus, and will save\nthem in a dedicated collection in your Zotero library. You can then\nreview the proposed papers and decide which ones you want to read. Once\nyou have read a paper, you can move it to another collection in your\nZotero library, and ReadNext will learn from your feedback to improve\nthe quality of the proposed papers.\n\nReadNext is designed to be used with with an embedding system. It uses\nthe system to generate embeddings for the papers in your Zotero library,\nand will use these embeddings to identify papers that are similar to\nyour research focus. Two embedding systems are currently support: a\nlocal one using the `BAAI/bge-base-en` model from Hugging Face, and a\nremote one using the Cohere embedding service.\n\nReadNext is designed to be used with [arXiv](https://arxiv.org/), a free\nservice that provides access to scientific papers in the fields of\nmathematics, physics, astronomy, computer science, quantitative biology,\nstatistics, and quantitative finance. ReadNext will use arXiv to\nidentify the latest papers in your research focus, and will propose them\nto you as part of your daily routine.\n\nThe designed userflow is the following:\n\n1. As a Zotero user, I will create one or multiple \u201cFocus\u201d collections\n in my Zotero library. Those are the collections where I will add the\n papers that are the most interesting to my current research. It is\n expected that the content of those collections will change over time\n as my research focus and interests evolves.\n2. On a daily basis, I will run `readnext` in my terminal, or I will\n create a cron job to run it automatically for me.\n 1. ReadNext will fetch the latest papers from arXiv\n 2. ReadNext will identify the papers that are relevant to your\n research focus, as defined in Zotero\n 3. ReadNext will propose the relevant papers to me and add them to\n Zotero in a dedicated collection where proposed papers are saved\n3. I will go in Zotero, start to read the proposed papers, and if any\n are of a particular interest I will add them to one of the \u201cFocus\u201d\n collections\n4. ReadNext will learn from your feedback to improve the quality of the\n proposed papers\n\nNow, let\u2019s see how to actually do this.\n\n## Usage\n\n### Help\n\nAny time, you can get contextual help for any command like this:\n\n``` sh\nreadnext --help\n```\n\n``` sh\nreadnext personalized-papers --help\n```\n\nThose commands will tell you which arguments and options are available\nfor each command.\n\n### arXiv categories and subcategories\n\nYou can get the full list of arXiv categories and subcategories by\nrunning the following command:\n\n``` sh\nreadnext arxiv-top-categories\n```\n\n``` sh\nreadnext arxiv-sub-categories\n```\n\nThose are the categories where you can get specific new papers from\narXiv.\n\n### Getting new papers proposals\n\nTo get new papers proposals, you have to run the `personalized-papers`\ncommand. That command requires two arguments:\n\n- `category`: the arXiv top, or sub, category from which you want to get\n new papers proposals\n- `zotero_collection`: the name of the Zotero collection where your\n papers of interest are stored in Zotero. This is what we refer to as\n the \u201cFocus\u201d collection above. The name of the collection is case\n sensitive and should be exactly as written in Zotero.\n\nThen you also have three options available:\n\n- `--proposals-collection`: which tells ReadNext that you want to save\n the proposed papers in Zotero, in the Zotero Collection specified by\n the argument. If you don\u2019t use this option, ReadNext will only print\n the proposed papers in the terminal, but will not save them in Zotero.\n The default behaviour is that you don\u2019t save them in Zotero.\n- `--with-artifacts` / `-a`: which tells ReadNext that you want to save\n the artifacts (PDF file of the papers and their summarization) into\n Zotero. This is the recommended workflow, but it requires a lot more\n space in your Zotero account. If you want to do this, you will most\n likely need to subscribe to one of their paid option.\n- `--nb-proposals`: which tells ReadNext how many papers you want to be\n proposed. The default value is 10.\n\nThe following command will propose 3 papers from the `cs.AI` caterory,\nbased on the `Readnext-Focus-LLM` collection in my Zotero library, save\nthem in Zotero in the `Readnext-Propositions-LLM` with all related\nartifacts:\n\n``` sh\nreadnext personalized-papers cs.AI Readnext-Focus-LLM --proposals-collection=Readnext-Propositions-LLM --with-artifacts --nb-proposals=3\n```\n\nAs you can see, you can easily create a series of topics you want papers\nproposals around, where each of the topic is defined by a series of\nspecific papers that you read and found important for your research.\n\nHere is what it looks like in the terminal:\n\n\n\nHere is what it looks like in Zotero:\n\n\n\n## Future Work\n\nHere is a list of future work that could be done to improve ReadNext\nafter the initial release:\n\n- **Adding an Abstraction Layer for Multiple Embedding Services**:\n Currently, ReadNext utilizes Cohere for embeddings in its initial\n version. LangChain could serve as a potential abstraction layer to\n support multiple different embedding services.\n- **Expanding Paper Sources with an Abstraction Layer**: ReadNext aims\n to integrate additional paper sources beyond just arXiv. This will be\n facilitated by implementing an abstraction layer for seamless\n integration.\n- **Enhancing Test Coverage**: To improve testing, we will go beyond\n testing utility functions and incorporate mocks for external services,\n ensuring comprehensive test coverage.\n- **Interactive Configuration via Command Line Tool**: We plan to\n augment the command line tool\u2019s functionality, allowing users to\n configure it directly from the command line using appropriate prompts\n and interactions.\n- **Refining Paper Selection Process**: Currently, every time readnext\n is executed, it retrieves today\u2019s latest papers from arXiv, identifies\n relevant papers based on current interests, and matches them against\n the personal research focus. To further enhance this functionality, we\n may introduce additional capabilities, such as restricting proposed\n papers to today\u2019s papers only.\n\n## Contributions\n\nWe welcome contributions to ReadNext! If you\u2019d like to contribute,\nplease follow these steps:\n\n1. Fork the repository on GitHub.\n2. Create a new branch with a descriptive name:\n `git checkout -b feature/your-feature-name`\n3. Make your changes and commit them:\n `git commit -m \"Add feature: your feature name\"`\n4. Push your changes to your fork:\n `git push origin feature/your-feature-name`\n5. Submit a pull request to the `main` branch of the original\n repository.\n",
"bugtrack_url": null,
"license": "GNU GPLv3",
"summary": "ReadNext suggests the best papers for you to read next from the ArXiv.",
"version": "0.0.6",
"project_urls": {
"Bug Tracker": "https://github.com/fgiasson/readnext/issues",
"Homepage": "https://github.com/fgiasson/readnext"
},
"split_keywords": [
"nbdev",
"jupyter",
"notebook",
"python"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "0196fa0cbd7f8121f1b1bd5ff878e71522a79eb731b9a58877eb5a385418059f",
"md5": "fa51e670d9f35610ff2253d9960558fc",
"sha256": "97685e1ddac22760b0866d3f65ef602678e29ae0df6541cae36dd55b1abbf2bb"
},
"downloads": -1,
"filename": "readnext-0.0.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "fa51e670d9f35610ff2253d9960558fc",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 31494,
"upload_time": "2023-10-04T13:21:04",
"upload_time_iso_8601": "2023-10-04T13:21:04.806079Z",
"url": "https://files.pythonhosted.org/packages/01/96/fa0cbd7f8121f1b1bd5ff878e71522a79eb731b9a58877eb5a385418059f/readnext-0.0.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "a9e1f3a3b17c96c92b73484093a2c7fa291bfff40de4a27d9d0858fbb3375ae7",
"md5": "438011245e7bb5181bc6fb4660a44452",
"sha256": "9e646a76ee658dc3078f6609c593abb2dd4c9d05895e8553b93cc5189d5289f9"
},
"downloads": -1,
"filename": "readnext-0.0.6.tar.gz",
"has_sig": false,
"md5_digest": "438011245e7bb5181bc6fb4660a44452",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 36296,
"upload_time": "2023-10-04T13:21:06",
"upload_time_iso_8601": "2023-10-04T13:21:06.525773Z",
"url": "https://files.pythonhosted.org/packages/a9/e1/f3a3b17c96c92b73484093a2c7fa291bfff40de4a27d9d0858fbb3375ae7/readnext-0.0.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-10-04 13:21:06",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "fgiasson",
"github_project": "ReadNext",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "readnext"
}
JSON
