# langchain-nexa-ai
This package contains the LangChain integration with [Nexa AI](https://www.nexa4ai.com/).
## Installation
```bash
pip install -U langchain-nexa-ai
```
And you should get an api key from [Nexa Hub](https://hub.nexa4ai.com/api_keys) and set it as an environment variable (`NEXA_API_KEY`)
## LLMs
`NexaAILLM` class exposes Octopus LLMs from NexaAI. We currently support four catogories: `shopping`, `conference`, `streaming`, and `travel`. See our [langchain-nexa-ai tutorial](./docs/tutorial.ipynb) and [Nexa AI documentation](https://docs.nexa4ai.com/docs/overview) for more details!
```python
from langchain_nexa_ai import NexaAILLM
octopus_llm = NexaAILLM()
result = octopus_llm.invoke("Show recommended products for electronics.", category="shopping")
print(result)
```
If `NEXA_API_KEY` is not set in env, you can also pass api_key as an argument when initializing:
```python
octopus_llm = NexaAILLM(api_key=api_key)
```
You can also pass a list of catogories (corresponding to each of your prompts) when using `generate` method of `NexaAILLM`.
```python
result = octopus_llm.generate(
prompts=[
"Show recommended products for electronics.",
"Find a Hotel to stay in Toyko from June 1 to June 10."
],
categories=[
"shopping",
"travel"
]
)
```
### Exploit LCEL
```python
from langchain_nexa_ai import NexaAILLM
from langchain_core.output_parsers import JsonOutputParser
octopus_llm = NexaAILLM()
parser = JsonOutputParser()
chain = octopus_llm | parser
result = chain.invoke(
input="Show me recommended electronics products",
config={
"llms": {
"NexaAILLM": {
"categories": ["shopping"]
}
}
}
)
print(result)
```
## Chat Models
Coming soon.
## TODO
- [ ] streaming
- [ ] docs
Raw data
{
"_id": null,
"home_page": "https://github.com/langchain-ai/langchain",
"name": "langchain-nexa-ai",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.8.1",
"maintainer_email": null,
"keywords": null,
"author": "Ethan Wang",
"author_email": "ethan@nexa4ai.com",
"download_url": "https://files.pythonhosted.org/packages/b5/9f/e7c177a308b6324adc167903e18aff6616fe8daa1b842810ae0c9152c5ac/langchain_nexa_ai-0.1.4.tar.gz",
"platform": null,
"description": "# langchain-nexa-ai\n\nThis package contains the LangChain integration with [Nexa AI](https://www.nexa4ai.com/).\n\n## Installation\n\n```bash\npip install -U langchain-nexa-ai\n```\n\nAnd you should get an api key from [Nexa Hub](https://hub.nexa4ai.com/api_keys) and set it as an environment variable (`NEXA_API_KEY`)\n\n## LLMs\n\n`NexaAILLM` class exposes Octopus LLMs from NexaAI. We currently support four catogories: `shopping`, `conference`, `streaming`, and `travel`. See our [langchain-nexa-ai tutorial](./docs/tutorial.ipynb) and [Nexa AI documentation](https://docs.nexa4ai.com/docs/overview) for more details!\n\n```python\nfrom langchain_nexa_ai import NexaAILLM\n\noctopus_llm = NexaAILLM()\nresult = octopus_llm.invoke(\"Show recommended products for electronics.\", category=\"shopping\")\nprint(result)\n```\n\nIf `NEXA_API_KEY` is not set in env, you can also pass api_key as an argument when initializing:\n\n```python\noctopus_llm = NexaAILLM(api_key=api_key)\n```\n\nYou can also pass a list of catogories (corresponding to each of your prompts) when using `generate` method of `NexaAILLM`.\n\n```python\nresult = octopus_llm.generate(\n prompts=[\n \"Show recommended products for electronics.\",\n \"Find a Hotel to stay in Toyko from June 1 to June 10.\"\n ],\n categories=[\n \"shopping\",\n \"travel\"\n ]\n)\n```\n\n### Exploit LCEL\n\n```python\nfrom langchain_nexa_ai import NexaAILLM\nfrom langchain_core.output_parsers import JsonOutputParser\n\noctopus_llm = NexaAILLM()\nparser = JsonOutputParser()\n\nchain = octopus_llm | parser\n\nresult = chain.invoke(\n input=\"Show me recommended electronics products\",\n config={\n \"llms\": {\n \"NexaAILLM\": {\n \"categories\": [\"shopping\"]\n }\n }\n }\n)\nprint(result)\n```\n\n## Chat Models\n\nComing soon.\n\n## TODO\n\n- [ ] streaming\n- [ ] docs\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "An integration package connecting NexaAI and LangChain",
"version": "0.1.4",
"project_urls": {
"Homepage": "https://github.com/langchain-ai/langchain",
"Repository": "https://github.com/langchain-ai/langchain",
"Source Code": "https://github.com/langchain-ai/langchain/tree/master/libs/partners/nexa-ai"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "379c53fae9f59d44e96c6f349279bda4fd23c65c80ef6883180b018cbb8ac09a",
"md5": "36bcbaf2d7c084c788549a4c050d76f0",
"sha256": "f47ab5841d09f6f4b60aa19e175717e8f4cbf0b7d07b27a6e13f980465d4fd55"
},
"downloads": -1,
"filename": "langchain_nexa_ai-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "36bcbaf2d7c084c788549a4c050d76f0",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.8.1",
"size": 4935,
"upload_time": "2024-07-02T00:52:36",
"upload_time_iso_8601": "2024-07-02T00:52:36.640058Z",
"url": "https://files.pythonhosted.org/packages/37/9c/53fae9f59d44e96c6f349279bda4fd23c65c80ef6883180b018cbb8ac09a/langchain_nexa_ai-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b59fe7c177a308b6324adc167903e18aff6616fe8daa1b842810ae0c9152c5ac",
"md5": "6bc97f7971f0fa1266d370fd6f2ba9c9",
"sha256": "eb64b73f1278b4c0465367ac21b7669baff9c0c8c70dd5dd56c5ca1f5716b8a6"
},
"downloads": -1,
"filename": "langchain_nexa_ai-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "6bc97f7971f0fa1266d370fd6f2ba9c9",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.8.1",
"size": 4676,
"upload_time": "2024-07-02T00:52:37",
"upload_time_iso_8601": "2024-07-02T00:52:37.643430Z",
"url": "https://files.pythonhosted.org/packages/b5/9f/e7c177a308b6324adc167903e18aff6616fe8daa1b842810ae0c9152c5ac/langchain_nexa_ai-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-07-02 00:52:37",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "langchain-ai",
"github_project": "langchain",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "langchain-nexa-ai"
}
JSON
