hamawhitegg / autogen4j Goto Github PK

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

No response

Use case

No response

Related issues

No response

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

No response

Use case

No response

Related issues

No response

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

There is no longer an AiClient that is compatible with OpenAI, capable of accessing other Large Language Model (LLM) Open APIs, and also has access to local large models.

What I desire in a Java version is likely present in a Python version, where llm_config can function with other LLM Open APIs.

Use case

var joe = AssistantAgent.builder()
                .client(OpenAiClient.builder()
                        .openaiApiBase(URL)
                        .openaiApiKey(API_KEY)
                        .build().init())
                .name("joe")
                .systemMessage("Your name is Joe and you are a part of a duo of comedians.")
                .humanInputMode(NEVER)
                .build();

https://github.com/feuyeux/hello-autogen/blob/main/hello-autogen-java/src/test/java/org/feuyeux/ai/autogen/HelloAutogenTests.java

local_llm_config = {
    "config_list": [
        {
            "model": "NotRequired",  # Loaded with LiteLLM command
            "api_key": "NotRequired",  # Not needed
            "base_url": "http://0.0.0.0:4000"  # Your LiteLLM URL
        }
    ],
    "cache_seed": None  # Turns off caching, useful for testing different models
}

joe = ConversableAgent(
    "joe",
    system_message="Your name is Joe and you are a part of a duo of comedians.",
    llm_config=local_llm_config,
    human_input_mode="NEVER",  # Never ask for human input.
)

https://github.com/feuyeux/hello-autogen/blob/main/hello-autogen-python/hello_autogen.py

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

Auto Generated Agent Chat: Task Solving with Code Generation, Execution & Debugging

Use case

No response

Related issues

No response

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

No response

Use case

No response

Related issues

No response

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

Auto Generated Agent Chat: Group Chat

Use case

No response

Related issues

No response

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

Auto Generated Agent Chat: Task Solving with Provided Tools as Functions

Use case

No response

Related issues

No response

Search before asking

• I had searched in the issues and found no similar optimization requirement.

Description

Oh, I apologize for the confusion. There was a minor issue with how I used the arxiv library.

The arxiv.Search object doesn't have a get() method. Instead, the arxiv.Search objects are iterable, so we should directly iterate over the result of the search.

Here's the corrected python code:

# filename: fetch_arxiv_papers.py
import arxiv
import datetime
from operator import itemgetter

def fetch_gpt_4_papers():
    search = arxiv.Search(
        query='gpt-4',
        max_results=1000,
        sort_by=arxiv.SortCriterion.SubmittedDate
    )
    papers = []
    for result in search.results():
        papers.append({
            'title': result.title,
            'authors': result.authors,
            'url': result.entry_id,
            'published': result.published,
            'summary': result.summary
        })

    papers_sorted = sorted(papers, key=itemgetter('published'), reverse=True)
    return papers_sorted

def main():
    papers = fetch_gpt_4_papers()
    for paper in papers:
        print('Title: ', paper['title'])
        print('Authors: ', ', '.join(paper['authors']))
        print('Published Date: ', paper['published'].strftime("%Y-%m-%d"))
        print('URL: ', paper['url'])
        print('Abstract: ', paper['summary'])
        print('\n\n')

if __name__ == "__main__":
    main()

You can save this Python script as 'fetch_arxiv_papers.py' and run it as follows:

python fetch_arxiv_papers.py

This script will print out the details of the latest papers about GPT-4 from arXiv.org. After running the script, use your language analyzing skills to read the abstracts and find out the potential applications of GPT-4 in software from these papers.

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

No response

Use case

No response

Related issues

No response