Name | llama-index-readers-pandas-ai JSON |
Version |
0.2.0
JSON |
| download |
home_page | None |
Summary | llama-index readers pandas_ai integration |
upload_time | 2024-08-22 14:32:06 |
maintainer | jerryjliu |
docs_url | None |
author | Your Name |
requires_python | <4.0,>=3.9 |
license | MIT |
keywords |
ai
pandas
|
VCS |
|
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# Pandas AI Loader
```bash
pip install llama-index-readers-pandas-ai
```
This loader is a light wrapper around the `PandasAI` Python package.
See here: https://github.com/gventuri/pandas-ai.
You can directly get the result of `pandasai.run` command, or
you can choose to load in `Document` objects via `load_data`.
## Usage
```python
from pandasai.llm.openai import OpenAI
import pandas as pd
# Sample DataFrame
df = pd.DataFrame(
{
"country": [
"United States",
"United Kingdom",
"France",
"Germany",
"Italy",
"Spain",
"Canada",
"Australia",
"Japan",
"China",
],
"gdp": [
21400000,
2940000,
2830000,
3870000,
2160000,
1350000,
1780000,
1320000,
516000,
14000000,
],
"happiness_index": [7.3, 7.2, 6.5, 7.0, 6.0, 6.3, 7.3, 7.3, 5.9, 5.0],
}
)
llm = OpenAI()
from llama_index.readers.pandas_ai import PandasAIReader
# use run_pandas_ai directly
# set is_conversational_answer=False to get parsed output
loader = PandasAIReader(llm=llm)
response = reader.run_pandas_ai(
df, "Which are the 5 happiest countries?", is_conversational_answer=False
)
print(response)
# load data with is_conversational_answer=False
# will use our PandasCSVReader under the hood
docs = reader.load_data(
df, "Which are the 5 happiest countries?", is_conversational_answer=False
)
# load data with is_conversational_answer=True
# will use our PandasCSVReader under the hood
docs = reader.load_data(
df, "Which are the 5 happiest countries?", is_conversational_answer=True
)
```
This loader is designed to be used as a way to load data into [LlamaIndex](https://github.com/run-llama/llama_index/).
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-readers-pandas-ai",
"maintainer": "jerryjliu",
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "ai, pandas",
"author": "Your Name",
"author_email": "you@example.com",
"download_url": "https://files.pythonhosted.org/packages/23/b8/598846edf7552e4a7f56ece265d5db23284ec0fd3ebde19cd3d76a9d8809/llama_index_readers_pandas_ai-0.2.0.tar.gz",
"platform": null,
"description": "# Pandas AI Loader\n\n```bash\npip install llama-index-readers-pandas-ai\n```\n\nThis loader is a light wrapper around the `PandasAI` Python package.\n\nSee here: https://github.com/gventuri/pandas-ai.\n\nYou can directly get the result of `pandasai.run` command, or\nyou can choose to load in `Document` objects via `load_data`.\n\n## Usage\n\n```python\nfrom pandasai.llm.openai import OpenAI\nimport pandas as pd\n\n# Sample DataFrame\ndf = pd.DataFrame(\n {\n \"country\": [\n \"United States\",\n \"United Kingdom\",\n \"France\",\n \"Germany\",\n \"Italy\",\n \"Spain\",\n \"Canada\",\n \"Australia\",\n \"Japan\",\n \"China\",\n ],\n \"gdp\": [\n 21400000,\n 2940000,\n 2830000,\n 3870000,\n 2160000,\n 1350000,\n 1780000,\n 1320000,\n 516000,\n 14000000,\n ],\n \"happiness_index\": [7.3, 7.2, 6.5, 7.0, 6.0, 6.3, 7.3, 7.3, 5.9, 5.0],\n }\n)\n\nllm = OpenAI()\n\nfrom llama_index.readers.pandas_ai import PandasAIReader\n\n# use run_pandas_ai directly\n# set is_conversational_answer=False to get parsed output\nloader = PandasAIReader(llm=llm)\nresponse = reader.run_pandas_ai(\n df, \"Which are the 5 happiest countries?\", is_conversational_answer=False\n)\nprint(response)\n\n# load data with is_conversational_answer=False\n# will use our PandasCSVReader under the hood\ndocs = reader.load_data(\n df, \"Which are the 5 happiest countries?\", is_conversational_answer=False\n)\n\n# load data with is_conversational_answer=True\n# will use our PandasCSVReader under the hood\ndocs = reader.load_data(\n df, \"Which are the 5 happiest countries?\", is_conversational_answer=True\n)\n```\n\nThis loader is designed to be used as a way to load data into [LlamaIndex](https://github.com/run-llama/llama_index/).\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index readers pandas_ai integration",
"version": "0.2.0",
"project_urls": null,
"split_keywords": [
"ai",
" pandas"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "0273b3dc890d2b173d1a3b827d6506b10b70e9993637919b470a919b7c6c04db",
"md5": "9f3be2331eecc3972d807b2fdfd0733b",
"sha256": "cc034dd7eca5c6e06ea1e663c264b20e90d623ed4c73cac13697a8b1cbf4f653"
},
"downloads": -1,
"filename": "llama_index_readers_pandas_ai-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "9f3be2331eecc3972d807b2fdfd0733b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 3582,
"upload_time": "2024-08-22T14:32:05",
"upload_time_iso_8601": "2024-08-22T14:32:05.203497Z",
"url": "https://files.pythonhosted.org/packages/02/73/b3dc890d2b173d1a3b827d6506b10b70e9993637919b470a919b7c6c04db/llama_index_readers_pandas_ai-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "23b8598846edf7552e4a7f56ece265d5db23284ec0fd3ebde19cd3d76a9d8809",
"md5": "e369365eb3bd130f8e4322fb3ce03a4f",
"sha256": "8926cf4742c1b79de04c3c5637c3ec3d08b132cc50119cc341ab4c6bbb06c0d8"
},
"downloads": -1,
"filename": "llama_index_readers_pandas_ai-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "e369365eb3bd130f8e4322fb3ce03a4f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 3323,
"upload_time": "2024-08-22T14:32:06",
"upload_time_iso_8601": "2024-08-22T14:32:06.921137Z",
"url": "https://files.pythonhosted.org/packages/23/b8/598846edf7552e4a7f56ece265d5db23284ec0fd3ebde19cd3d76a9d8809/llama_index_readers_pandas_ai-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-22 14:32:06",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-readers-pandas-ai"
}