llama-index-llms-opea

Name	llama-index-llms-opea JSON
Version	0.1.0 JSON
	download
home_page	None
Summary	llama-index llms opea integration
upload_time	2025-01-15 15:54:58
maintainer	None
docs_url	None
author	Logan Markewich
requires_python	<4.0,>=3.8.1
license	MIT
keywords
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # LlamaIndex Llms Integration: OPEA LLM

OPEA (Open Platform for Enterprise AI) is a platform for building, deploying, and scaling AI applications. As part of this platform, many core gen-ai components are available for deployment as microservices, including LLMs.

Visit [https://opea.dev](https://opea.dev) for more information, and their [GitHub](https://github.com/opea-project/GenAIComps) for the source code of the OPEA components.

## Installation

1. Install the required Python packages:

```bash
%pip install llama-index-llms-opea
```

## Usage

```python
from llama_index.core.llms import ChatMessage
from llama_index.llms.opea import OPEA

llm = OPEA(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    api_base="http://localhost:8080/v1",
    temperature=0.7,
    max_tokens=256,
    additional_kwargs={"top_p": 0.95},
)

# Complete a prompt
response = llm.complete("What is the capital of France?")
print(response)

# Stream a chat response
response = llm.stream_chat(
    [ChatMessage(role="user", content="What is the capital of France?")]
)
for chunk in response:
    print(chunk.delta, end="", flush=True)
```

All available methods include:

- `complete()`
- `stream_complete()`
- `chat()`
- `stream_chat()`

as well as async versions of the methods with the `a` prefix.

            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "llama-index-llms-opea",
    "maintainer": null,
    "docs_url": null,
    "requires_python": "<4.0,>=3.8.1",
    "maintainer_email": null,
    "keywords": null,
    "author": "Logan Markewich",
    "author_email": "logan@runllama.ai",
    "download_url": "https://files.pythonhosted.org/packages/75/2e/9be7aa99e072648a4ad1a620478359de70d11116effb409363f2e965c825/llama_index_llms_opea-0.1.0.tar.gz",
    "platform": null,
    "description": "# LlamaIndex Llms Integration: OPEA LLM\n\nOPEA (Open Platform for Enterprise AI) is a platform for building, deploying, and scaling AI applications. As part of this platform, many core gen-ai components are available for deployment as microservices, including LLMs.\n\nVisit [https://opea.dev](https://opea.dev) for more information, and their [GitHub](https://github.com/opea-project/GenAIComps) for the source code of the OPEA components.\n\n## Installation\n\n1. Install the required Python packages:\n\n```bash\n%pip install llama-index-llms-opea\n```\n\n## Usage\n\n```python\nfrom llama_index.core.llms import ChatMessage\nfrom llama_index.llms.opea import OPEA\n\nllm = OPEA(\n    model=\"meta-llama/Meta-Llama-3.1-8B-Instruct\",\n    api_base=\"http://localhost:8080/v1\",\n    temperature=0.7,\n    max_tokens=256,\n    additional_kwargs={\"top_p\": 0.95},\n)\n\n# Complete a prompt\nresponse = llm.complete(\"What is the capital of France?\")\nprint(response)\n\n# Stream a chat response\nresponse = llm.stream_chat(\n    [ChatMessage(role=\"user\", content=\"What is the capital of France?\")]\n)\nfor chunk in response:\n    print(chunk.delta, end=\"\", flush=True)\n```\n\nAll available methods include:\n\n- `complete()`\n- `stream_complete()`\n- `chat()`\n- `stream_chat()`\n\nas well as async versions of the methods with the `a` prefix.\n",
    "bugtrack_url": null,
    "license": "MIT",
    "summary": "llama-index llms opea integration",
    "version": "0.1.0",
    "project_urls": null,
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "d3b467c2f7d1cb81a63b831aeeb27aa4bd13c504f4dcf1bc03113c5e3aed02c5",
                "md5": "52e1a17b7f00ef12538bad09b71c54cd",
                "sha256": "fc3bdf30b05f6ac1f60c90e955a62e3ab0359c618165f09371ba7349245fe5b4"
            },
            "downloads": -1,
            "filename": "llama_index_llms_opea-0.1.0-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "52e1a17b7f00ef12538bad09b71c54cd",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": "<4.0,>=3.8.1",
            "size": 2533,
            "upload_time": "2025-01-15T15:54:56",
            "upload_time_iso_8601": "2025-01-15T15:54:56.744775Z",
            "url": "https://files.pythonhosted.org/packages/d3/b4/67c2f7d1cb81a63b831aeeb27aa4bd13c504f4dcf1bc03113c5e3aed02c5/llama_index_llms_opea-0.1.0-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "752e9be7aa99e072648a4ad1a620478359de70d11116effb409363f2e965c825",
                "md5": "85de6473eb58977380eac738a947fb30",
                "sha256": "d6a7c33cf276f1b2ab8990546e0ed828d87594c76df1cb45951322fa1168dd94"
            },
            "downloads": -1,
            "filename": "llama_index_llms_opea-0.1.0.tar.gz",
            "has_sig": false,
            "md5_digest": "85de6473eb58977380eac738a947fb30",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": "<4.0,>=3.8.1",
            "size": 2242,
            "upload_time": "2025-01-15T15:54:58",
            "upload_time_iso_8601": "2025-01-15T15:54:58.371470Z",
            "url": "https://files.pythonhosted.org/packages/75/2e/9be7aa99e072648a4ad1a620478359de70d11116effb409363f2e965c825/llama_index_llms_opea-0.1.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2025-01-15 15:54:58",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "lcname": "llama-index-llms-opea"
}