docs: add template for raising github issues (#156)

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,36 @@
+name: Feature request
+description: Submit a proposal/request for a new aios feature
+title: "[Feature] "
+labels: ["feature request"]
+
+body:
+- type: checkboxes
+  attributes:
+    label: Checked other resources
+    description: Please confirm and check all the following options.
+    options:
+      - label: I added a very descriptive title to this issue.
+        required: true
+      - label: I am sure the issue hasn't been already addressed by searching through https://github.com/agiresearch/AIOS/issues.
+        required: true
+- type: textarea
+  attributes:
+    label: The feature, motivation and pitch
+    description: >
+      A clear and concise description of the feature proposal. Please outline the motivation for the proposal. Is your feature request related to a specific problem? e.g., *"I'm working on X and would like Y to be possible"*. If this is related to another GitHub issue, please link here too.
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: Alternatives
+    description: >
+      A description of any alternative solutions or features you've considered, if any.
+- type: textarea
+  attributes:
+    label: Additional context
+    description: >
+      Add any other context or screenshots about the feature request.
+- type: markdown
+  attributes:
+    value: >
+      Thanks for contributing 🎉!

.github/ISSUE_TEMPLATE/misc-discussion.yml

@@ -0,0 +1,17 @@
+name: Misc/random discussions that do not fit into the above categories.
+description: Submit a discussion as you like. Note that developers are heavily overloaded and we mainly rely on community users to answer these issues.
+title: "[Misc] "
+labels: ["misc discussion"]
+
+body:
+- type: textarea
+  attributes:
+    label: Anything you want to discuss about aios.
+    description: >
+      Anything you want to discuss about aios.
+  validations:
+    required: true
+- type: markdown
+  attributes:
+    value: >
+      Thanks for contributing 🎉!

.github/ISSUE_TEMPLATE/new-llm-endpoint.yml

@@ -0,0 +1,33 @@
+name: Request for a new llm endpoint support
+description: Submit a proposal/request for a new llm endpoint.
+title: "[New LLM-Endpoint] "
+labels: ["new llm endpoint"]
+
+body:
+- type: checkboxes
+  attributes:
+    label: Checked other resources
+    description: Please confirm and check all the following options.
+    options:
+      - label: I added a very descriptive title to this issue.
+        required: true
+      - label: I am sure the issue hasn't been already addressed by searching through https://github.com/agiresearch/AIOS/issues.
+        required: true
+      - label: I am sure the new endpoint is not supported by aios currently by looking through https://github.com/agiresearch/aios/tree/main/aios/llm_kernel/llm_classes.
+        required: true
+- type: textarea
+  attributes:
+    label: The llm endpoint to consider.
+    description: >
+      An endpoint url, pointing to the llm endpoint that is good to integrate, e.g. https://ollama.com/ .
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: What's your expected advantage of integrating the llm endpoint?
+    description: >
+      For example, lower latency, cost-free, cpu-only enabled?
+- type: markdown
+  attributes:
+    value: >
+      Thanks for contributing 🎉!

.github/ISSUE_TEMPLATE/usage.yml

@@ -0,0 +1,35 @@
+name: Usage
+description: Raise an issue here if you don't know how to use aios.
+title: "[Usage] "
+labels: ["usage"]
+
+body:
+- type: checkboxes
+  attributes:
+    label: Checked other resources
+    description: Please confirm and check all the following options.
+    options:
+      - label: I added a very descriptive title to this issue.
+        required: true
+      - label: I am sure the issue hasn't been already addressed by searching through https://github.com/agiresearch/AIOS/issues.
+        required: true
+      - label: The usage issue is not resolved by updating to the latest stable version in the main branch.
+        required: true
+- type: textarea
+  attributes:
+    label: Your current environment
+    description: |
+      Your current environment information (including OS, GPU, Cuda-version)
+  validations:
+    required: true
+- type: textarea
+  attributes:
+    label: How would you like to use aios
+    description: |
+      A detailed description of how you want to use aios.
+    value: |
+      I want to run aios with the llm endpoint: xxx for agent: xxx.
+- type: markdown
+  attributes:
+    value: >
+      Thanks for contributing 🎉!

README.md

@@ -5,6 +5,8 @@
 [![Code License](https://img.shields.io/badge/Code%20License-MIT-green.svg)](https://github.com/agiresearch/AIOS/blob/main/LICENSE)
 <a href='https://discord.gg/B2HFxEgTJX'><img src='https://img.shields.io/badge/Community-Discord-8A2BE2'></a>
 
+<a href="https://trendshift.io/repositories/8908" target="_blank"><img src="https://trendshift.io/api/badge/repositories/8908" alt="agiresearch%2FAIOS | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
 AIOS, a Large Language Model (LLM) Agent operating system, embeds large language model into Operating Systems (OS) as the brain of the OS, enabling an operating system "with soul" -- an important step towards AGI. AIOS is designed to optimize resource allocation, facilitate context switch across agents, enable concurrent execution of agents, provide tool service for agents, maintain access control for agents, and provide a rich set of toolkits for LLM Agent developers.
 
 
@@ -169,12 +171,12 @@ You could also run the models locally:
 python eval.py --llm_name meta-llama/Meta-Llama-3-8B-Instruct --max_gpu_memory '{"0": "24GB"}' --eval_device "cuda:0" --max_new_tokens 256 --agents MathAgent:1,TravelAgent:1 --mode concurrent-only
 ```
 
-### Supported LLM backbones
-- gpt-3.5-turbo, gpt-4, gpt-4o
-- gemini-1.0-pro, gemini-1.5-flash-latest, gemini-1.5-pro-latest
+### Supported LLM Endpoints
+- OpenAI API
+- Gemini API
 - ollama
-- claude3
-- open-sourced LLM from Huggingface
+- vllm
+- native huggingface models (locally)
 
 ## 🖋️ References
 ```

aios/llm_kernel/llm_classes/gemini_llm.py

@@ -63,13 +63,11 @@ def process(self,
         if tools:
             messages = self.tool_calling_input_format(messages, tools)
 
-            # convert role to fit the gemini role types
+        # convert role to fit the gemini role types
         messages = self.convert_messages(
             messages=messages,
         )
 
-        # print(messages)
-        # TODO: add tool calling
         self.logger.log(
             f"{agent_process.agent_name} is switched to executing.\n",
             level = "executing"

aios/llm_kernel/llms.py

@@ -3,7 +3,7 @@
 # All abstractions will be implemented here
 
 from .llm_classes.model_registry import MODEL_REGISTRY
-from .llm_classes.open_llm import OpenLLM
+from .llm_classes.huggingface_native_llm import OpenLLM
 
 # standard implementation of LLM methods
 from .llm_classes.ollama_llm import OllamaLLM