Skip to content

Commit f054dbd

Browse files
adilhafeezadilhafeez
authored
update quick start to elevate gateway/proxy example (#671)
1 parent 41aa4ab commit f054dbd

File tree

1 file changed

+104
-100
lines changed

1 file changed

+104
-100
lines changed

‎docs/source/get_started/quickstart.rst‎

Lines changed: 104 additions & 100 deletions
Original file line numberDiff line numberDiff line change
@@ -5,9 +5,9 @@ Quickstart
55

66
Follow this guide to learn how to quickly set up Plano and integrate it into your generative AI applications. You can:
77

8+
- :ref:`Use Plano as a model proxy (Gateway) <llm_routing_quickstart>` to standardize access to multiple LLM providers.
89
- :ref:`Build agents <quickstart_agents>` for multi-step workflows (e.g., travel assistants with flights and hotels).
910
- :ref:`Call deterministic APIs via prompt targets <quickstart_prompt_targets>` to turn instructions directly into function calls.
10-
- :ref:`Use Plano as a model proxy (Gateway) <llm_routing_quickstart>` to standardize access to multiple LLM providers.
1111

1212
.. note::
1313
This quickstart assumes basic familiarity with agents and prompt targets from the Concepts section. For background, see :ref:`Agents <agents>` and :ref:`Prompt Target <prompt_target>`.
@@ -48,6 +48,109 @@ Plano's CLI allows you to manage and interact with the Plano efficiently. To ins
4848
$ pip install planoai==0.4.1
4949
5050
51+
.. _llm_routing_quickstart:
52+
53+
Use Plano as a Model Proxy (Gateway)
54+
------------------------------------
55+
56+
Step 1. Create plano config file
57+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
58+
59+
Plano operates based on a configuration file where you can define LLM providers, prompt targets, guardrails, etc. Below is an example configuration that defines OpenAI and Anthropic LLM providers.
60+
61+
Create ``plano_config.yaml`` file with the following content:
62+
63+
.. code-block:: yaml
64+
65+
version: v0.3.0
66+
67+
listeners:
68+
- type: model
69+
name: model_1
70+
address: 0.0.0.0
71+
port: 12000
72+
73+
model_providers:
74+
75+
- access_key: $OPENAI_API_KEY
76+
model: openai/gpt-4o
77+
default: true
78+
79+
- access_key: $ANTHROPIC_API_KEY
80+
model: anthropic/claude-sonnet-4-5
81+
82+
Step 2. Start plano
83+
~~~~~~~~~~~~~~~~~~~
84+
85+
Once the config file is created, ensure that you have environment variables set up for ``ANTHROPIC_API_KEY`` and ``OPENAI_API_KEY`` (or these are defined in a ``.env`` file).
86+
87+
Start Plano:
88+
89+
.. code-block:: console
90+
91+
$ planoai up plano_config.yaml
92+
# Or if installed with uv tool: uvx planoai up plano_config.yaml
93+
2024-12-05 11:24:51,288 - planoai.main - INFO - Starting plano cli version: 0.4.1
94+
2024-12-05 11:24:51,825 - planoai.utils - INFO - Schema validation successful!
95+
2024-12-05 11:24:51,825 - planoai.main - INFO - Starting plano
96+
...
97+
2024-12-05 11:25:16,131 - planoai.core - INFO - Container is healthy!
98+
99+
Step 3: Interact with LLM
100+
~~~~~~~~~~~~~~~~~~~~~~~~~
101+
102+
Step 3.1: Using curl command
103+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
104+
105+
.. code-block:: bash
106+
107+
$ curl --header 'Content-Type: application/json' \
108+
--data '{"messages": [{"role": "user","content": "What is the capital of France?"}], "model": "none"}' \
109+
http://localhost:12000/v1/chat/completions
110+
111+
{
112+
...
113+
"model": "gpt-4o-2024-08-06",
114+
"choices": [
115+
{
116+
...
117+
"messages": {
118+
"role": "assistant",
119+
"content": "The capital of France is Paris.",
120+
},
121+
}
122+
],
123+
}
124+
125+
.. note::
126+
When the requested model is not found in the configuration, Plano will randomly select an available model from the configured providers. In this example, we use ``"model": "none"`` and Plano selects the default model ``openai/gpt-4o``.
127+
128+
Step 3.2: Using OpenAI Python client
129+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
130+
131+
Make outbound calls via the Plano gateway:
132+
133+
.. code-block:: python
134+
135+
from openai import OpenAI
136+
137+
# Use the OpenAI client as usual
138+
client = OpenAI(
139+
# No need to set a specific openai.api_key since it's configured in Plano's gateway
140+
api_key='--',
141+
# Set the OpenAI API base URL to the Plano gateway endpoint
142+
base_url="http://127.0.0.1:12000/v1"
143+
)
144+
145+
response = client.chat.completions.create(
146+
# we select model from plano_config file
147+
model="--",
148+
messages=[{"role": "user", "content": "What is the capital of France?"}],
149+
)
150+
151+
print("OpenAI Response:", response.choices[0].message.content)
152+
153+
51154
Build Agentic Apps with Plano
52155
-----------------------------
53156

@@ -228,105 +331,6 @@ And to get the list of supported currencies:
228331
"Here is a list of the currencies that are supported for conversion from USD, along with their symbols:\n\n1. AUD - Australian Dollar\n2. BGN - Bulgarian Lev\n3. BRL - Brazilian Real\n4. CAD - Canadian Dollar\n5. CHF - Swiss Franc\n6. CNY - Chinese Renminbi Yuan\n7. CZK - Czech Koruna\n8. DKK - Danish Krone\n9. EUR - Euro\n10. GBP - British Pound\n11. HKD - Hong Kong Dollar\n12. HUF - Hungarian Forint\n13. IDR - Indonesian Rupiah\n14. ILS - Israeli New Sheqel\n15. INR - Indian Rupee\n16. ISK - Icelandic Króna\n17. JPY - Japanese Yen\n18. KRW - South Korean Won\n19. MXN - Mexican Peso\n20. MYR - Malaysian Ringgit\n21. NOK - Norwegian Krone\n22. NZD - New Zealand Dollar\n23. PHP - Philippine Peso\n24. PLN - Polish Złoty\n25. RON - Romanian Leu\n26. SEK - Swedish Krona\n27. SGD - Singapore Dollar\n28. THB - Thai Baht\n29. TRY - Turkish Lira\n30. USD - United States Dollar\n31. ZAR - South African Rand\n\nIf you want to convert USD to any of these currencies, you can select the one you are interested in."
229332
230333
231-
.. _llm_routing_quickstart:
232-
233-
Use Plano as a Model Proxy (Gateway)
234-
------------------------------------
235-
236-
Step 1. Create plano config file
237-
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
238-
239-
Plano operates based on a configuration file where you can define LLM providers, prompt targets, guardrails, etc. Below is an example configuration that defines OpenAI and Anthropic LLM providers.
240-
241-
Create ``plano_config.yaml`` file with the following content:
242-
243-
.. code-block:: yaml
244-
245-
version: v0.3.0
246-
247-
listeners:
248-
- type: model
249-
name: model_1
250-
address: 0.0.0.0
251-
port: 12000
252-
253-
model_providers:
254-
255-
- access_key: $OPENAI_API_KEY
256-
model: openai/gpt-4o
257-
default: true
258-
259-
- access_key: $ANTHROPIC_API_KEY
260-
model: anthropic/claude-sonnet-4-5
261-
262-
Step 2. Start plano
263-
~~~~~~~~~~~~~~~~~~~
264-
265-
Once the config file is created, ensure that you have environment variables set up for ``ANTHROPIC_API_KEY`` and ``OPENAI_API_KEY`` (or these are defined in a ``.env`` file).
266-
267-
Start Plano:
268-
269-
.. code-block:: console
270-
271-
$ planoai up plano_config.yaml
272-
# Or if installed with uv tool: uvx planoai up plano_config.yaml
273-
2024-12-05 11:24:51,288 - planoai.main - INFO - Starting plano cli version: 0.4.1
274-
2024-12-05 11:24:51,825 - planoai.utils - INFO - Schema validation successful!
275-
2024-12-05 11:24:51,825 - planoai.main - INFO - Starting plano
276-
...
277-
2024-12-05 11:25:16,131 - planoai.core - INFO - Container is healthy!
278-
279-
Step 3: Interact with LLM
280-
~~~~~~~~~~~~~~~~~~~~~~~~~
281-
282-
Step 3.1: Using OpenAI Python client
283-
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
284-
285-
Make outbound calls via the Plano gateway:
286-
287-
.. code-block:: python
288-
289-
from openai import OpenAI
290-
291-
# Use the OpenAI client as usual
292-
client = OpenAI(
293-
# No need to set a specific openai.api_key since it's configured in Plano's gateway
294-
api_key='--',
295-
# Set the OpenAI API base URL to the Plano gateway endpoint
296-
base_url="http://127.0.0.1:12000/v1"
297-
)
298-
299-
response = client.chat.completions.create(
300-
# we select model from plano_config file
301-
model="--",
302-
messages=[{"role": "user", "content": "What is the capital of France?"}],
303-
)
304-
305-
print("OpenAI Response:", response.choices[0].message.content)
306-
307-
Step 3.2: Using curl command
308-
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
309-
310-
.. code-block:: bash
311-
312-
$ curl --header 'Content-Type: application/json' \
313-
--data '{"messages": [{"role": "user","content": "What is the capital of France?"}], "model": "none"}' \
314-
http://localhost:12000/v1/chat/completions
315-
316-
{
317-
...
318-
"model": "gpt-4o-2024-08-06",
319-
"choices": [
320-
{
321-
...
322-
"messages": {
323-
"role": "assistant",
324-
"content": "The capital of France is Paris.",
325-
},
326-
}
327-
],
328-
}
329-
330334
Next Steps
331335
==========
332336

0 commit comments

Comments
 (0)