Skip to content

Commit 832a1dd

Browse files
committed
add pre-requisites and links to the examples in the repo directly instead of relative links
1 parent c355661 commit 832a1dd

File tree

1 file changed

+13
-5
lines changed

1 file changed

+13
-5
lines changed

daprdocs/content/en/python-sdk-docs/conversation.md

Lines changed: 13 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,3 @@
1-
---
21
title: "Conversation API (Python) – Recommended Usage"
32
linkTitle: "Conversation"
43
weight: 11000
@@ -13,10 +12,18 @@ The Dapr Conversation API is currently in alpha. This page presents the recommen
1312
- Async variants
1413
- Important safety notes for executing tool calls
1514

15+
## Prerequisites
16+
17+
- [Dapr CLI]({{% ref install-dapr-cli.md %}}) installed
18+
- Initialized [Dapr environment]({{% ref install-dapr-selfhost.md %}})
19+
- [Python 3.9+](https://www.python.org/downloads/) installed
20+
- [Dapr Python package]({{% ref "python#installation" %}}) installed
21+
- A configured LLM component (for example, OpenAI or Azure OpenAI) in your Dapr environment
22+
1623
For full, end‑to‑end flows and provider setup, see:
17-
- The examples in the SDK repo under `examples/conversation/`
18-
- `TOOL-CALL-QUICKSTART.md`
19-
- `real_llm_providers_example.py`
24+
- The SDK examples under Conversation:
25+
- [TOOL-CALL-QUICKSTART.md](https://github.com/dapr/python-sdk/blob/main/examples/conversation/TOOL-CALL-QUICKSTART.md)
26+
- [real_llm_providers_example.py](https://github.com/dapr/python-sdk/blob/main/examples/conversation/real_llm_providers_example.py)
2027

2128
## Plain conversation (no tools)
2229

@@ -47,7 +54,8 @@ Key points:
4754

4855
## Tools: decorator‑based (recommended)
4956

50-
Decorator-based tools offer a clean, ergonomic approach. Define a function with clear type hints and (optional) docstring; decorate it with `@conversation.tool`. Registered tools can be passed to the LLM and invoked via tool calls.
57+
Decorator-based tools offer a clean, ergonomic approach. Define a function with clear type hints and detail docstring, this is important for the LLM to understand how or when to invoke the tool;
58+
decorate it with `@conversation.tool`. Registered tools can be passed to the LLM and invoked via tool calls.
5159

5260
```python
5361
from dapr.clients import DaprClient

0 commit comments

Comments
 (0)