| Name | grafo-ai-tools JSON |
| Version |
0.1.3
JSON |
| download |
| home_page | None |
| Summary | A set of tools for easily interacting with LLMs. |
| upload_time | 2025-09-03 23:43:33 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.11 |
| license | MIT |
| keywords |
ai
agents
llm
workflows
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Install
```
uv add grafo-ai-tools
```
# WHAT
A set of tools for easily interacting with LLMs.
# WHY
Building AI-driven software leans upon a number of utilities, such as prompt building and LLM calling via HTTP requests. Additionally, writing agents and workflows can prove particularly challenging using conventional code structures.
# HOW
This simple library offers a set of predefined functions for:
- Easy prompting - you need only provide a path
- Calling LLMs - instructor takes care of that for us
- Modifying response models - we use Pydantic (duh)
Additionally, we provide `grafo` out of the box for convenient workflow building.
## About Grafo
Grafo (see Recommended Docs below) is a library for building executable DAGs where each node contains a coroutine. Since the DAG abstraction fits particularly well into AI-driven building, we have provided the `BaseWorkflow` class with the following methods:
- `task` for LLM calling
- `redirect` to help you manage redirections in your `grafo` workflows
# Examples
### Simple text:
```python
from ait import AIT
ait = AIT("gpt-5")
path = "./prompt.md"
response = ait.chat(path)
print(response.completion)
print(response.content)
```
### Structured response:
```python
from ait import AIT
from pydantic import BaseModel
class Purchase(BaseModel):
product: str
quantity: int
ait = AIT("gpt-5")
path = "./prompt.md" # PROMPT: {{ message }}
message = "I want to buy 5 apples"
response = ait.asend(response_model=Fruit, path=path, message=message)
```
### Structured response with model type injection:
```python
from ait import AIT
from pydantic import BaseModel
class Purchase(BaseModel):
product: str
quantity: int
ait = AIT("gpt-5")
path = "./prompt.md" # PROMPT: {{ message }}
message = "I want to buy 5 apples"
available_fruits = ["apple", "banana", "orange"]
FruitModel = ait.inject_types(Purchase, [
("product", Literal[tuple(available_fruits)])
])
response = ait.asend(response_model=Purchase, path=path, message=message)
```
### Simple workflow:
```python
from ait import AIT, BaseWorkflow, Node
from pydantic import BaseModel
class Purchase(BaseModel):
product: str
quantity: int
class Eval(BaseModel):
is_valid: bool
reasoning: str
humanized_failure_reason: str | None
ait = AIT("gpt-5")
prompts_path = "./"
message = "I want to buy 5 apples"
available_fruits = ["apple", "banana", "orange"]
FruitModel = ait.inject_types(Purchase, [
("product", Literal[tuple(available_fruits)])
])
class PurchaseWorkflow(BaseWorkflow):
def __init__(...):
...
async def run(self, message) -> Purchase:
purchase_node = Node[FruitModel](
uuid="fruit purchase node"
coroutine=self.task
kwargs=dict(
path=f"{prompts_path}/purchase.md"
response_model=FruitModel
message=message
)
)
validation_node = Node[Eval](
uuid="purchase eval node"
coroutine=self.task
kwargs=dict(
path=f"{prompts_path}/eval.md"
response_model=Eval
message=message
purchase=lambda: purchase_node.output
)
)
eval_node.on_after_run = (
self.redirect,
dict(
source_node=purchase_node
validation_node=validation_node
)
)
await purchase_node.connect(validation_node)
executor = TreeExecutor(uuid="Purchase Workflow", roots=[purchase_node])
await executor.run()
if not purchase_node.output or not validation_node.output.is_valid:
raise ValueError("Purchase failed.")
return purchase_node.output
```
## Recommended Docs
- `instructor` https://python.useinstructor.com/
- `jinja2` https://jinja.palletsprojects.com/en/stable/
- `pydantic` https://docs.pydantic.dev/latest/
- `grafo` https://github.com/paulomtts/grafo
Raw data
{
"_id": null,
"home_page": null,
"name": "grafo-ai-tools",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "ai, agents, llm, workflows",
"author": null,
"author_email": "\"@paulomtts\" <paulomtts@outlook.com>",
"download_url": "https://files.pythonhosted.org/packages/37/fb/b3e41ef48ed7ef778b3ff11c6468daf32ba8670532cc1b723cd23a354ccc/grafo_ai_tools-0.1.3.tar.gz",
"platform": null,
"description": "# Install\n```\nuv add grafo-ai-tools\n```\n\n# WHAT\nA set of tools for easily interacting with LLMs.\n\n# WHY\nBuilding AI-driven software leans upon a number of utilities, such as prompt building and LLM calling via HTTP requests. Additionally, writing agents and workflows can prove particularly challenging using conventional code structures.\n\n# HOW\nThis simple library offers a set of predefined functions for:\n- Easy prompting - you need only provide a path\n- Calling LLMs - instructor takes care of that for us\n- Modifying response models - we use Pydantic (duh)\n\nAdditionally, we provide `grafo` out of the box for convenient workflow building.\n\n## About Grafo\nGrafo (see Recommended Docs below) is a library for building executable DAGs where each node contains a coroutine. Since the DAG abstraction fits particularly well into AI-driven building, we have provided the `BaseWorkflow` class with the following methods:\n- `task` for LLM calling\n- `redirect` to help you manage redirections in your `grafo` workflows\n\n# Examples\n### Simple text:\n```python\nfrom ait import AIT\n\nait = AIT(\"gpt-5\")\npath = \"./prompt.md\"\nresponse = ait.chat(path)\nprint(response.completion)\nprint(response.content)\n```\n\n### Structured response:\n```python\nfrom ait import AIT\nfrom pydantic import BaseModel\n\nclass Purchase(BaseModel):\n product: str\n quantity: int\n\nait = AIT(\"gpt-5\")\npath = \"./prompt.md\" # PROMPT: {{ message }}\nmessage = \"I want to buy 5 apples\"\nresponse = ait.asend(response_model=Fruit, path=path, message=message)\n```\n\n### Structured response with model type injection:\n```python\nfrom ait import AIT\nfrom pydantic import BaseModel\n\nclass Purchase(BaseModel):\n product: str\n quantity: int\n\nait = AIT(\"gpt-5\")\npath = \"./prompt.md\" # PROMPT: {{ message }}\nmessage = \"I want to buy 5 apples\"\navailable_fruits = [\"apple\", \"banana\", \"orange\"]\nFruitModel = ait.inject_types(Purchase, [\n (\"product\", Literal[tuple(available_fruits)])\n])\nresponse = ait.asend(response_model=Purchase, path=path, message=message)\n```\n\n### Simple workflow:\n```python\nfrom ait import AIT, BaseWorkflow, Node\nfrom pydantic import BaseModel\n\nclass Purchase(BaseModel):\n product: str\n quantity: int\n\nclass Eval(BaseModel):\n is_valid: bool\n reasoning: str\n humanized_failure_reason: str | None\n\nait = AIT(\"gpt-5\")\nprompts_path = \"./\"\nmessage = \"I want to buy 5 apples\"\navailable_fruits = [\"apple\", \"banana\", \"orange\"]\nFruitModel = ait.inject_types(Purchase, [\n (\"product\", Literal[tuple(available_fruits)])\n])\n\nclass PurchaseWorkflow(BaseWorkflow):\n def __init__(...):\n ...\n\n async def run(self, message) -> Purchase:\n purchase_node = Node[FruitModel](\n uuid=\"fruit purchase node\"\n coroutine=self.task\n kwargs=dict(\n path=f\"{prompts_path}/purchase.md\"\n response_model=FruitModel\n message=message\n )\n )\n validation_node = Node[Eval](\n uuid=\"purchase eval node\"\n coroutine=self.task\n kwargs=dict(\n path=f\"{prompts_path}/eval.md\"\n response_model=Eval\n message=message\n purchase=lambda: purchase_node.output\n )\n )\n eval_node.on_after_run = (\n self.redirect,\n dict(\n source_node=purchase_node\n validation_node=validation_node\n )\n )\n await purchase_node.connect(validation_node)\n executor = TreeExecutor(uuid=\"Purchase Workflow\", roots=[purchase_node])\n await executor.run()\n\n if not purchase_node.output or not validation_node.output.is_valid:\n raise ValueError(\"Purchase failed.\")\n\n return purchase_node.output\n```\n\n## Recommended Docs\n- `instructor` https://python.useinstructor.com/\n- `jinja2` https://jinja.palletsprojects.com/en/stable/\n- `pydantic` https://docs.pydantic.dev/latest/\n- `grafo` https://github.com/paulomtts/grafo\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A set of tools for easily interacting with LLMs.",
"version": "0.1.3",
"project_urls": {
"Homepage": "https://github.com/paulomtts/Grafo-AI-Tools.git"
},
"split_keywords": [
"ai",
" agents",
" llm",
" workflows"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "d29f128cab2ebb205ddf5dc90c8da1c210f2b683efcf9847670300a0c69c6ad9",
"md5": "72c824e473f497c537272b1c68045d01",
"sha256": "8d53d6430de309f944cec89732a2544d204dbe7872842a3cf1964ef2b6121c32"
},
"downloads": -1,
"filename": "grafo_ai_tools-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "72c824e473f497c537272b1c68045d01",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 14435,
"upload_time": "2025-09-03T23:43:32",
"upload_time_iso_8601": "2025-09-03T23:43:32.333728Z",
"url": "https://files.pythonhosted.org/packages/d2/9f/128cab2ebb205ddf5dc90c8da1c210f2b683efcf9847670300a0c69c6ad9/grafo_ai_tools-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "37fbb3e41ef48ed7ef778b3ff11c6468daf32ba8670532cc1b723cd23a354ccc",
"md5": "b641d64edca878e7aa82debcb2746ed6",
"sha256": "9f5a6f6b576553c1c026d47115403785c3fc955f13437b37be89766d616b61cd"
},
"downloads": -1,
"filename": "grafo_ai_tools-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "b641d64edca878e7aa82debcb2746ed6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 11782,
"upload_time": "2025-09-03T23:43:33",
"upload_time_iso_8601": "2025-09-03T23:43:33.214157Z",
"url": "https://files.pythonhosted.org/packages/37/fb/b3e41ef48ed7ef778b3ff11c6468daf32ba8670532cc1b723cd23a354ccc/grafo_ai_tools-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-03 23:43:33",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "paulomtts",
"github_project": "Grafo-AI-Tools",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "grafo-ai-tools"
}
