Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ThejasNU/readme and docs sync and updates #57

Merged
merged 3 commits into from
Jan 22, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 14 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -34,13 +34,23 @@ The mono-repo for the Couchbase Agent Catalog project.
git clone https://github.com/couchbaselabs/agent-catalog
```

3. You are now ready to install the Agent Catalog package! We recommend using Anaconda to create a virtual environment
for your project to ensure no global dependencies interfere with the project.
Using your project's Python environment, execute the following command to install a local package with `pip`:
3. You are now ready to install the Agent Catalog package!
<br/>We recommend using Anaconda to create a virtual environment for your project to ensure no global dependencies interfere with the project.

[Click here](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html) for Anaconda installation steps.

Once anaconda or any of its distribution is installed, execute the following commands to activate the environment.

```bash
conda create -n agentcenv python=3.12

conda activate agentcenv
```
Alternatively, you can use any Python virtual environment manager.

Once environment is set up, execute the following command to install a local package with `pip`:
```bash
cd agent-catalog
source $MY_PYTHON_ENVIRONMENT

# Install the agentc package.
pip install libs/agentc
Expand Down
23 changes: 23 additions & 0 deletions docs/source/faqs.rst
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,14 @@ Feel free to use your favorite framework (e.g., LangChain, LangGraph, Controlflo
application!
For our examples (see `here <https://github.com/couchbaselabs/agent-catalog-example>`_), we use Controlflow.

What services do I need to enable on my Couchbase cluster?
-----------------------------------------------------------

Enable the following services on your Couchbase cluster:
- Data, Query, Index: For storing items and searching them.
- Search: For performing vector search on items.
- Analytics: For creating views on audit logs and to query the views for better insights on logs.

What does Agent Catalog add to my Couchbase bucket?
---------------------------------------------------

Expand Down Expand Up @@ -101,6 +109,13 @@ Inside this scope, two collections are created:
Agent Catalog also creates GSI indexes on these collections (to optimize tool / prompt retrieval) as well as vector
indexes on the ``<kind>_catalog`` collection for tool / prompt semantic search.

Do I need Couchbase instance to run Agent Catalog?
--------------------------------------------------

No, you do not need a Couchbase instance to run Agent Catalog.

If couchbase credentials are not provided in the environment variables file, Agent Catalog will use only the local catalog.
For functionalities such as :command:`find`, :command:`execute` if couchbase credentials are not mentioned, only the local catalog will be used for searching tools/prompts.

What is Agent Catalog doing when I run ``agentc index``?
--------------------------------------------------------
Expand Down Expand Up @@ -381,3 +396,11 @@ Yes!
Agent Catalog does not restrict you to a specific language model.
You are free to choose any LLM for your agent workflow development (provided your chosen agent framework supports
the LLM you choose).

Why am I not able to install Agent Catalog(agentc) because of PyTorch error?
--------------------------------------------------------------------

While installing agentc, you may face a dependency clash between the PyTorch version installed globally in your system and the PyTorch version being installed by the Sentence transformers library in agentc. This likely happens when the globally installed PyTorch is of a different version as compared to the one agentc requires.

You can resolve this by using Anaconda or any other virtual environment manager instead of the in-built python venv manager. We have found Anaconda to be better in terms of isolating project dependencies. In case this does not solve the issue and you are on an older OS, considering using a Virtual Machine to run your application.

32 changes: 22 additions & 10 deletions docs/source/install.rst
Original file line number Diff line number Diff line change
Expand Up @@ -18,23 +18,35 @@ Building From Source (with pip)
1. Make sure you have Python 3.12 and `Poetry <https://python-poetry.org/docs/#installation>`_ installed!

2. Clone this repository.
Make sure you have your SSH key setup!

.. code-block:: bash

git clone https://github.com/couchbaselabs/agent-catalog

3. You are now ready to install the Agent Catalog package!
Using your project's Python environment, execute the following command to install a local package with
:command:`pip`:

We recommend using Anaconda to create a virtual environment for your project to ensure no global dependencies interfere with the project.

`Click here <https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html>`_ for Anaconda installation steps.

Once anaconda or any of its distribution is installed, execute the following commands to activate the environment.

.. code-block:: bash

cd agent-catalog
source $MY_PYTHON_ENVIRONMENT
conda create -n agentcenv python=3.12

conda activate agentcenv

Alternatively, you can use any Python virtual environment manager.

Once environment is set up, execute the following command to install a local package with :command:`pip`:

.. code-block:: bash

cd agent-catalog

# Install the agentc package.
pip install libs/agentc
# Install the agentc package.
pip install libs/agentc

If you are interested in building a ``.whl`` file (for later use in ``.whl``-based installs), use :command:`poetry`
directly:
Expand Down Expand Up @@ -99,12 +111,12 @@ some libraries like numpy need to be built, subsequent runs will be faster).
execute Search and execute a specific tool.
find Find items from the catalog based on a natural language QUERY string or by name.
index Walk the source directory trees (SOURCE_DIRS) to index source files into the local catalog.
ls List all tools or prompts in the catalog.
publish Upload the local catalog to a Couchbase instance.
ls List all indexed tools and/or prompts in the catalog.
publish Upload the local catalog and/or logs to a Couchbase instance.
status Show the status of the local catalog.
version Show the current version of agentc.

See: https://docs.couchbase.com for more information.
See: https://docs.couchbase.com or https://couchbaselabs.github.io/agent-catalog/index.html# for more information.

If you see the output above, you are all set!
To build your first agent, head on over to the `user guide <guide.html>`_ page.
11 changes: 8 additions & 3 deletions templates/agents/with_controlflow/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -25,10 +25,10 @@ This directory contains a starter project for building agents with Couchbase, Co

4. Installing anaconda.
We recommend using Anaconda to create a virtual environment for your project to ensure no global dependencies interfere with the project.

[Click here](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html) for installation steps.

Once anaconda or any of its distribution is installed, execute the following commands to active the environment.
[Click here](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html) for Anaconda installation steps.

Once anaconda or any of its distribution is installed, execute the following commands to activate the environment.

```bash
conda create -n travel-agent python=3.12
Expand Down Expand Up @@ -101,6 +101,11 @@ This directory contains a starter project for building agents with Couchbase, Co

3. For those interested in using Capella, see [here](https://cloud.couchbase.com/sign-up).

Once Couchbase instance is running, enable the following services on your Couchbase cluster:
- Data, Query, Index: For storing items and searching them.
- Search: For performing vector search on items.
- Analytics: For creating views on audit logs and to query the views for better insights on logs.

This specific agent also uses the `travel-sample` bucket.
You'll need to navigate to your instance's UI (for local instances, this is on http://localhost:8091) to install
this sample bucket.
Expand Down
10 changes: 8 additions & 2 deletions templates/agents/with_langgraph/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -26,9 +26,9 @@ This directory contains a starter project for building agents with Couchbase, La
4. Installing anaconda.
We recommend using Anaconda to create a virtual environment for your project to ensure no global dependencies interfere with the project.

[Click here](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html) for installation steps.
[Click here](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html) for Anaconda installation steps.

Once anaconda or any of its distribution is installed, execute the following commands to active the environment.
Once anaconda or any of its distribution is installed, execute the following commands to activate the environment.

```bash
conda create -n research-agent python=3.12
Expand Down Expand Up @@ -76,6 +76,7 @@ This directory contains a starter project for building agents with Couchbase, La
Note that `tools` and `prompts` are _relative paths_ to the `tools` and `prompts` folder.

```bash
# agentc index $PATH_TO_TOOLS_FOLDER $PATH_TO_PROMPTS_FOLDER
agentc index tools prompts
```

Expand All @@ -100,6 +101,11 @@ This directory contains a starter project for building agents with Couchbase, La

3. For those interested in using Capella, see [here](https://cloud.couchbase.com/sign-up).

Once Couchbase instance is running, enable the following services on your Couchbase cluster:
- Data, Query, Index: For storing items and searching them.
- Search: For performing vector search on items.
- Analytics: For creating views on audit logs and to query the views for better insights on logs.

This specific agent also uses the `travel-sample` bucket.
You'll need to navigate to your instance's UI (for local instances, this is on http://localhost:8091) to import
this sample bucket.
Expand Down
Loading