# Runpod LLM API Endpoint Lib for LangChain
[](https://badge.fury.io/py/langchain-runpod-llm)
## Installation
```
# Install the latest release version
pip install runpod-llm
# or
# Install the latest development version (main branch)
pip install git+https://https://github.com/tsangwailam/langchain-runpod-llm
```
## Get Runpod API key
1. Goto www.runpod.io. Create a RunPod account.
2. From the portal, goto Settings>APIKeys
3. Create a new API key by click the "+ API Key" button.
## Usage
```python
from runpod_llm import RunpodLlama2
llm = RunpodLlama2(
apikey="YOU_RUNPOD_API_KEY",
llm_type="7b|13b",
config={
"max_tokens": 500,
#Maximum number of tokens to generate per output sequence.
"n": 1, # Number of output sequences to return for the given prompt.
"best_of": 1, # Number of output sequences that are generated from the prompt. From these best_of sequences, the top n sequences are returned. best_of must be greater than or equal to n. This is treated as the beam width when use_beam_search is True. By default, best_of is set to n.
"Presence penalty": 0.2, # Float that penalizes new tokens based on whether they appear in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.
"Frequency penalty": 0.5, # Float that penalizes new tokens based on their frequency in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.
"temperature": 0.3, # Float that controls the randomness of the sampling. Lower values make the model more deterministic, while higher values make the model more random. Zero means greedy sampling.
"top_p": 1, # Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens.
"top_k": -1, # Integer that controls the number of top tokens to consider. Set to -1 to consider all tokens.
"use_beam_search": False, # Whether to use beam search instead of sampling.
},
verbose=True, # verbose output
)
some_prompt_template = xxxxx
output_chain = some_prompt_template | llm
output_chain.invoke({"input":"some input to prompt template"})
```
Raw data
{
"_id": null,
"home_page": "https://github.com/tsangwailam/langchain-runpod-llm",
"name": "langchain-runpod-llm",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "runpod, ai, langchain, llm, llama2, SDK, API, python, library",
"author": "William Tsang",
"author_email": "William Tsang <contact@williamtsang.me>",
"download_url": "https://files.pythonhosted.org/packages/64/61/e0db8a82ae97f0553947ba7cc98c8344c819b5a678e0fb7e82945002c5e8/langchain_runpod_llm-0.0.5.tar.gz",
"platform": null,
"description": "# Runpod LLM API Endpoint Lib for LangChain\n[](https://badge.fury.io/py/langchain-runpod-llm)\n\n## Installation\n\n```\n# Install the latest release version\npip install runpod-llm\n\n# or\n\n# Install the latest development version (main branch)\npip install git+https://https://github.com/tsangwailam/langchain-runpod-llm\n```\n\n## Get Runpod API key\n\n1. Goto www.runpod.io. Create a RunPod account.\n2. From the portal, goto Settings>APIKeys\n3. Create a new API key by click the \"+ API Key\" button.\n\n## Usage\n\n```python\nfrom runpod_llm import RunpodLlama2\n\nllm = RunpodLlama2(\n apikey=\"YOU_RUNPOD_API_KEY\",\n llm_type=\"7b|13b\",\n config={\n \"max_tokens\": 500, \n #Maximum number of tokens to generate per output sequence.\n \"n\": 1, # Number of output sequences to return for the given prompt.\n \"best_of\": 1, # Number of output sequences that are generated from the prompt. From these best_of sequences, the top n sequences are returned. best_of must be greater than or equal to n. This is treated as the beam width when use_beam_search is True. By default, best_of is set to n.\n \"Presence penalty\": 0.2, # Float that penalizes new tokens based on whether they appear in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.\n \"Frequency penalty\": 0.5, # Float that penalizes new tokens based on their frequency in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.\n \"temperature\": 0.3, # Float that controls the randomness of the sampling. Lower values make the model more deterministic, while higher values make the model more random. Zero means greedy sampling.\n \"top_p\": 1, # Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens.\n \"top_k\": -1, # Integer that controls the number of top tokens to consider. Set to -1 to consider all tokens.\n \"use_beam_search\": False, # Whether to use beam search instead of sampling.\n },\n verbose=True, # verbose output\n )\n\n some_prompt_template = xxxxx\n output_chain = some_prompt_template | llm\n output_chain.invoke({\"input\":\"some input to prompt template\"})\n```\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "\ud83d\udc0d | Python library for langchain using RunPod API endpoint as LLM.",
"version": "0.0.5",
"project_urls": {
"Bug Tracker": "https://github.com/tsangwailam/langchain-runpod-llm/issues",
"Changelog": "https://github.com/tsangwailam/langchain-runpod-llm/blob/main/CHANGELOG.md",
"Documentation": "https://github.com/tsangwailam/langchain-runpod-llm/blob/main/README.md",
"Homepage": "https://github.com/tsangwailam/langchain-runpod-llm",
"Repository": "https://github.com/tsangwailam/langchain-runpod-llm"
},
"split_keywords": [
"runpod",
" ai",
" langchain",
" llm",
" llama2",
" sdk",
" api",
" python",
" library"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "e9645dbeeb2a4dff6770f572655ef1b7420e98ae2ef12e3c92e5b739393b5666",
"md5": "5a61f7060d9c1a6b8b0f18c569ca089b",
"sha256": "ee4248db8b46101fafb32b04821af9fb3020806cb35268d381a898112913856b"
},
"downloads": -1,
"filename": "langchain_runpod_llm-0.0.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5a61f7060d9c1a6b8b0f18c569ca089b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.9",
"size": 10207,
"upload_time": "2024-07-13T17:17:16",
"upload_time_iso_8601": "2024-07-13T17:17:16.478748Z",
"url": "https://files.pythonhosted.org/packages/e9/64/5dbeeb2a4dff6770f572655ef1b7420e98ae2ef12e3c92e5b739393b5666/langchain_runpod_llm-0.0.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "6461e0db8a82ae97f0553947ba7cc98c8344c819b5a678e0fb7e82945002c5e8",
"md5": "5ba62975d01ab6272f35d3b149ba1bca",
"sha256": "1cc87ef70c3819a1aacacdd092c80c7cb2911c3acb3ba6459452f5dcfb99aded"
},
"downloads": -1,
"filename": "langchain_runpod_llm-0.0.5.tar.gz",
"has_sig": false,
"md5_digest": "5ba62975d01ab6272f35d3b149ba1bca",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.9",
"size": 9021,
"upload_time": "2024-07-13T17:17:18",
"upload_time_iso_8601": "2024-07-13T17:17:18.041081Z",
"url": "https://files.pythonhosted.org/packages/64/61/e0db8a82ae97f0553947ba7cc98c8344c819b5a678e0fb7e82945002c5e8/langchain_runpod_llm-0.0.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-13 17:17:18",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "tsangwailam",
"github_project": "langchain-runpod-llm",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "langchain-runpod-llm"
}
JSON
