superagent-ai / superagent Goto Github PK

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Add a replicate Tool that can work together with an agent.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

Getting Started

To get started with SuperAgent, follow these steps:

1. Clone the SuperAgent repository into a public GitHub repository or fork it from https://github.com/homanp/superagent/fork. If you plan to distribute the code, keep the source code public.

   git clone https://github.com/homanp/superagent.git

2. Set up your .env file.

   cp .env.example .env

   • Configure the environment variables according to your requirements.

3. To run the script, simply execute it using:

   bash setup.sh

You can save the script in a file, e.g., setup.sh,

#!/bin/bash

# Create and activate the virtual environment
virtualenv venv
source venv/bin/activate

# Install dependencies using Poetry
poetry install

# Run Prisma migration
poetry run prisma migrate dev

# Start the application with auto-reload
uvicorn app.main:app --reload

This script streamlines the setup process by creating the virtual environment, installing dependencies, performing the Prisma migration, and starting the application with auto-reload. It helps ensure a consistent and efficient development environment for Python web applications.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

In order to do more granular logging and debugging for an agent we should handle all callbacks from the Agent or enable a more verbose logging.

This PR is connected to #64

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Create a scheduler that can either:

• Keep vector indexes up to date.
• Run agents

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

Wolfram Alpha makes all systematic knowledge immediately computable and accessible to everyone.
https://www.wolframalpha.com/

Summary

Add endpoints for retrieving a user.

Summary

Use prisma as ORM and add authentication.

Summary

Use black, flake8 for formatting and linting

Summary

A user should be able to attach documents/vectorstores for QA

Summary

An API token should be present when running an Agent.

The display button in digital ocean does not work.

An error is thrown when it is observed that the example file does not exist.

Summary

A user should be able to invocate Agents using a JWT token. These tokens need a separate DB with the following fields:

description, token

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Would be great if we could add unit tests to Superagent.

✔️ Solution

Use pytest test suite to add unit tests and integration tests to Superagent.

❓ Alternatives

No response

📝 Additional Context

No response

Acknowledgements

• My issue title is concise, descriptive, and in title casing.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

Summary

Add the llm field to Agent model. Should be of type JSONB.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

We should introduce versioning of the prompts in order for users to track/evaluate different versions of a specific prompt. Similar to what Replicate does with their models.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

A user should be able to update a prompt

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

Summary

Create a DB schema for Agents.

name
type react, plan-solve

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Sometimes queries take a long time to execute. When that happens it would be nice to offer webhooks for more flexible DX.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

Hey there, is there a possibility, to add:
https://supabase.com/blog/openai-embeddings-postgres-vector

instead of going with pinecone? So in this way we could store the embeddings also locally.

There is an existing project "SuperAgent" which is a popular NPM package for performing requests.
In order to avoid impacting the searchability for each project changing the name would be an effective solution.

Summary

Add retrieval chain if an Agent has a Document connected to it.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

The Agent lib is getting bigger for each feature we release. Instead of running everything in the same class we should create a AgentBase and implement common features there.

Each new Agent should inherit from the AgentBase class.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

Summary

Create a prompt model containing the following:

name
template -> Large text field
inputs -> JSON
type -> QA prompt etc.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Autonomous Agents such as AutoGPT or BabyAGI would be a great Agent type to bring into Superagent.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

somehow it is not installing dependencies.

If I add this

   virtualenv venv
   source venv/bin/activate

then it is installing dependencies

To run the project from the root directory

   uvicorn app.main:app --reload

Summary

Add memory to agents

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Add a new type of Agent that specializes on content aggreation.

This would be an ideal issue to use Llama Index for.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

Summary

To keep the code consistent we should move the models from the api folder to the lib folder.

lib
--models
  --agents

Summary

The invocation endpoint should take a separate API token and has a single key in the payload called message.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Sometimes, users will upsert documents that need to be more "real-time". Possibility to update the indexes with new content would be a useful feature for this.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

A user should be able to add multiple documents to an Agent.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

Summary

In order to introduce spending limits we would want to save the token usage for an agent in the DB

Expected behaviour

Create a new DB table for saving tokens and cost estimations.
Each run should be saved as a run entry.
One to many relationship between usage and agent.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Add a new type of tool that enables an Agent to do real-time search via Bing or Google.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Users want to be able to control settings such as max_tokens, temperature etc.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Implement the OpenAI Agent type.

https://github.com/hwchase17/langchain/blob/master/docs/modules/agents/tools/tools_as_openai_functions.ipynb

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

One of the great things about @huggingface face is the race to build what I call "mini" models suited for specific use cases. Wrap those models around a specific Agent and you build amazing apps.

Superagent should support these mini models wrapped so that they can be used with Agents.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

All Agent callbacks and intermediate steps should be stored in a log.

✔️ Solution

TBD

❓ Alternatives

No response

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Create a browser agent that can search the web and aggregate content.

This could be followed up with controlling the browser in future PRs.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

Hey, we I am currently working with @thesushilsharma and we are looking for ways to integrate the GPT4ALL LLM in order to use it as our native LLM instead of the one provided by OpenAI. Are there any methods existing at this stage which would allow us to achieve this?

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Add support for pulling in Llamaindex into Superagent.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

To solve this issue

run this command after the poetry installation

poetry run prisma migrate dev

then run

uvicorn app.main:app --reload

shortcut command to duplicate the .env.example to .env

cp .env.example .env

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

Some tools require additional authentication params on runtime. Examples of such tools are Wolfram. The API should support passing required authentication methods similar to YAML documents.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.

⚠️ Please check that this feature request hasn't been suggested before.

• I searched previous Ideas in Discussions didn't find any similar feature requests.
• I searched previous Issues didn't find any similar feature requests.

🔖 Feature description

A user should be able to set a prompt on a Document QA Agent.

📝 Additional Context

No response

Acknowledgements

• My issue title is concise and descriptive.
• I have searched the existing issues to make sure this feature has not been requested yet.
• I have provided enough information for the maintainers to understand and evaluate this request.