From 7403a3fc74a287cdd9b20dd5d0933e1bdf1ac3f0 Mon Sep 17 00:00:00 2001
From: kodaline <doncheva.adelina@gmail.com>
Date: Thu, 16 May 2024 23:59:49 +0200
Subject: [PATCH] imp: update of tool prompt

updated the actual tool prompt currently in the core
---
 mkdocs/conceptual/prompts/instructions.md | 63 +++++++++++++++++------
 1 file changed, 48 insertions(+), 15 deletions(-)

diff --git a/mkdocs/conceptual/prompts/instructions.md b/mkdocs/conceptual/prompts/instructions.md
index 7b6ceefa0..504d851fa 100644
--- a/mkdocs/conceptual/prompts/instructions.md
+++ b/mkdocs/conceptual/prompts/instructions.md
@@ -1,6 +1,6 @@
 # Instructions Prompt
 
-The Instruction Prompt explains the [Tool Agent](../cheshire_cat/agent.md#tool-chain) how to format its reasoning.  
+The Instruction Prompt explains the [Tool Agent](../cheshire_cat/agent.md#tool-chain) how to format its reasoning.
 The [Tool Agent](../cheshire_cat/agent.md) uses a [chain](https://docs.langchain.com/docs/components/chains/llm-chain)
 to decide *when* and *which* [tool](../plugins.md) is the most appropriate to fulfill the user's needs.
 
@@ -8,19 +8,52 @@ By default, it is set to Langchain [instructions format](https://api.python.lang
 which looks like this:
 
 ```python
-instructions = """
-To use a tool, please use the following format:
-
-Thought: Do I need to use a tool? Yes
-Action: the action to take, should be one of [{tool_names}]
-Action Input: the input to the action
-Observation: the result of the action
-
-When you have a response to say to the Human, or if you do not need to use a tool, you MUST use the format:
-
-Thought: Do I need to use a tool? No
-
-AI: [your response here]"""
+instructions = """Create a JSON action to complete the action sequence, with the correct "action" and "action_input" to help the Human.
+You can use one of these actions:
+{tools}
+- "final_answer": Use this action to finish or no relevant action is available. Input is always null.
+
+## To add an action, use only the following format:
+\```json
+{{
+    "action": // str - The name of the action to take, should be one of [{tool_names}, "final_answer"]
+    "action_input": // str or null - The input to the action
+}}
+\```
+
+{examples}
+
+## Action output
+After each action there will be an action output in this format:
+\```json
+{{
+    "action_output": // output of the preceding action
+}}
+\```
+
+## Final answer / no action available
+When you have a final answer (or no tools are relevant), use the following format:
+\```json
+{{
+    "action": "final_answer",
+    "action_input": null
+}}
+\```
+
+## Conversation with Human:
+{chat_history}
+
+## Actions sequence used until now:
+{agent_scratchpad}
+
+## Next action:
+\```json
+"""
 ```
 
-where the placeholder `{tool_names}` is replaced with the list of Python [tools](../plugins.md) retrieved from the [procedural memory](../memory/long_term_memory.md).
\ No newline at end of file
+where:
+
+- the placeholder `{tools}` is replaced with the list of Python [tools](../plugins.md) retrieved from the [procedural memory](../memory/long_term_memory.md);
+- the `{examples}` is replaced with some example actions given to the model;
+- the `{chat_history}` is replaced with the chat history with the user;
+- the `{agent_scratchpad}` is replaced with the agent scratchpad information about the actions' sequence used until that iteration.
\ No newline at end of file