Name | llama-index-llms-anyscale JSON |
Version |
0.3.0
JSON |
| download |
home_page | None |
Summary | llama-index llms anyscale integration |
upload_time | 2024-11-18 01:28:25 |
maintainer | None |
docs_url | None |
author | Your Name |
requires_python | <4.0,>=3.9 |
license | MIT |
keywords |
|
VCS |
|
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# LlamaIndex Llms Integration: Anyscale
### Installation
```bash
%pip install llama-index-llms-anyscale
!pip install llama-index
```
### Basic Usage
```py
from llama_index.llms.anyscale import Anyscale
from llama_index.core.llms import ChatMessage
# Call chat with ChatMessage List
# You need to either set env var ANYSCALE_API_KEY or set api_key in the class constructor
# Example of setting API key through environment variable
# import os
# os.environ['ANYSCALE_API_KEY'] = '<your-api-key>'
# Initialize the Anyscale LLM with your API key
llm = Anyscale(api_key="<your-api-key>")
# Chat Example
message = ChatMessage(role="user", content="Tell me a joke")
resp = llm.chat([message])
print(resp)
# Expected Output:
# assistant: Sure, here's a joke for you:
#
# Why couldn't the bicycle stand up by itself?
#
# Because it was two-tired!
#
# I hope that brought a smile to your face! Is there anything else I can assist you with?
```
### Streaming Example
```py
message = ChatMessage(role="user", content="Tell me a story in 250 words")
resp = llm.stream_chat([message])
for r in resp:
print(r.delta, end="")
# Output Example:
# Once upon a time, there was a young girl named Maria who lived in a small village surrounded by lush green forests.
# Maria was a kind and gentle soul, loved by everyone in the village. She spent most of her days exploring the forests,
# discovering new species of plants and animals, and helping the villagers with their daily chores...
# (Story continues until it reaches the word limit.)
```
### Completion Example
```py
resp = llm.complete("Tell me a joke")
print(resp)
# Expected Output:
# assistant: Sure, here's a joke for you:
#
# Why couldn't the bicycle stand up by itself?
#
# Because it was two-tired!
```
### Streaming Completion Example
```py
resp = llm.stream_complete("Tell me a story in 250 words")
for r in resp:
print(r.delta, end="")
# Example Output:
# Once upon a time, there was a young girl named Maria who lived in a small village...
# (Stream continues as the story is generated.)
```
### Model Configuration
```py
llm = Anyscale(model="codellama/CodeLlama-34b-Instruct-hf")
resp = llm.complete("Show me the c++ code to send requests to HTTP Server")
print(resp)
```
### LLM Implementation example
https://docs.llamaindex.ai/en/stable/examples/llm/anyscale/
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-llms-anyscale",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": "Your Name",
"author_email": "you@example.com",
"download_url": "https://files.pythonhosted.org/packages/10/b0/0dd5f3d598eb82527dcdfb80f1f98591b2a637b8c40732d43bb96fe0e638/llama_index_llms_anyscale-0.3.0.tar.gz",
"platform": null,
"description": "# LlamaIndex Llms Integration: Anyscale\n\n### Installation\n\n```bash\n%pip install llama-index-llms-anyscale\n!pip install llama-index\n```\n\n### Basic Usage\n\n```py\nfrom llama_index.llms.anyscale import Anyscale\nfrom llama_index.core.llms import ChatMessage\n\n# Call chat with ChatMessage List\n# You need to either set env var ANYSCALE_API_KEY or set api_key in the class constructor\n\n# Example of setting API key through environment variable\n# import os\n# os.environ['ANYSCALE_API_KEY'] = '<your-api-key>'\n\n# Initialize the Anyscale LLM with your API key\nllm = Anyscale(api_key=\"<your-api-key>\")\n\n# Chat Example\nmessage = ChatMessage(role=\"user\", content=\"Tell me a joke\")\nresp = llm.chat([message])\nprint(resp)\n\n# Expected Output:\n# assistant: Sure, here's a joke for you:\n#\n# Why couldn't the bicycle stand up by itself?\n#\n# Because it was two-tired!\n#\n# I hope that brought a smile to your face! Is there anything else I can assist you with?\n```\n\n### Streaming Example\n\n```py\nmessage = ChatMessage(role=\"user\", content=\"Tell me a story in 250 words\")\nresp = llm.stream_chat([message])\nfor r in resp:\n print(r.delta, end=\"\")\n\n# Output Example:\n# Once upon a time, there was a young girl named Maria who lived in a small village surrounded by lush green forests.\n# Maria was a kind and gentle soul, loved by everyone in the village. She spent most of her days exploring the forests,\n# discovering new species of plants and animals, and helping the villagers with their daily chores...\n# (Story continues until it reaches the word limit.)\n```\n\n### Completion Example\n\n```py\nresp = llm.complete(\"Tell me a joke\")\nprint(resp)\n\n# Expected Output:\n# assistant: Sure, here's a joke for you:\n#\n# Why couldn't the bicycle stand up by itself?\n#\n# Because it was two-tired!\n```\n\n### Streaming Completion Example\n\n```py\nresp = llm.stream_complete(\"Tell me a story in 250 words\")\nfor r in resp:\n print(r.delta, end=\"\")\n\n# Example Output:\n# Once upon a time, there was a young girl named Maria who lived in a small village...\n# (Stream continues as the story is generated.)\n```\n\n### Model Configuration\n\n```py\nllm = Anyscale(model=\"codellama/CodeLlama-34b-Instruct-hf\")\nresp = llm.complete(\"Show me the c++ code to send requests to HTTP Server\")\nprint(resp)\n```\n\n### LLM Implementation example\n\nhttps://docs.llamaindex.ai/en/stable/examples/llm/anyscale/\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index llms anyscale integration",
"version": "0.3.0",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "36e1c72804bf5f7f12abc8b0eb553c2a9019a63107d66d589e026b5e5694e687",
"md5": "c0b05e5d39a6a34b57a92f64fad9b4bd",
"sha256": "90655064f3ed05efa7f053ee9ddeb2dff9d39d20ef2a250e46045acb60e7e020"
},
"downloads": -1,
"filename": "llama_index_llms_anyscale-0.3.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c0b05e5d39a6a34b57a92f64fad9b4bd",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 5098,
"upload_time": "2024-11-18T01:28:24",
"upload_time_iso_8601": "2024-11-18T01:28:24.338488Z",
"url": "https://files.pythonhosted.org/packages/36/e1/c72804bf5f7f12abc8b0eb553c2a9019a63107d66d589e026b5e5694e687/llama_index_llms_anyscale-0.3.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "10b00dd5f3d598eb82527dcdfb80f1f98591b2a637b8c40732d43bb96fe0e638",
"md5": "77a604465e0cd0745d8b12aea3fea727",
"sha256": "187fddd7ba54aa929d19976b77f64fc370b4cfe6654316474e5644899384b290"
},
"downloads": -1,
"filename": "llama_index_llms_anyscale-0.3.0.tar.gz",
"has_sig": false,
"md5_digest": "77a604465e0cd0745d8b12aea3fea727",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 4388,
"upload_time": "2024-11-18T01:28:25",
"upload_time_iso_8601": "2024-11-18T01:28:25.838844Z",
"url": "https://files.pythonhosted.org/packages/10/b0/0dd5f3d598eb82527dcdfb80f1f98591b2a637b8c40732d43bb96fe0e638/llama_index_llms_anyscale-0.3.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-18 01:28:25",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-llms-anyscale"
}