fix bugs in clear and improve prompts

- [x] fix bugs in clear conversation in conversation history pure mode
- [x] modify system prompts for better instruction following
- [x] update readme for open-source model usage

InteRecAgent/README.md

@@ -109,6 +109,37 @@ InteRecAgent consists of 4 necessary components:
     bot_type="chat" # model type, ["chat", "completetion"]. For gpt-3.5-turbo and gpt-4, it should be "chat". For text-davinci-003, it should be "completetion" 
     ```
 
+    Meanwhile, we support to serve local models such as Vicuna as the backbone language model instead of OpenAI APIs:
+
+    1. Download the weights of [Vicuna](https://huggingface.co/lmsys/vicuna-7b-v1.5) from huggingface.
+
+    2. Install `fschat` package according to [FastChat](https://github.com/lm-sys/FastChat?tab=readme-ov-file#install)
+
+    3. Deploy the Vicuna model with OpenAI-Compatible RESTful APIs by running the following command:
+
+        ```bash
+        # First, launch the controller
+        python3 -m fastchat.serve.controller
+        # Then, launch the model worker(s)
+        python3 -m fastchat.serve.model_worker --model-path path-to-vicuna
+        # Finally, launch the RESTful API server
+        python3 -m fastchat.serve.openai_api_server --host localhost --port 8000
+        ```
+
+    4. Set the configuration for RecLlama API in `run.sh`
+
+        ```bash
+        API_KEY="EMPTY"
+        API_BASE="http://localhost:8000/v1"
+        API_VERSION="2023-03-15-preview"
+        API_TYPE="open_ai"
+        engine="vicuna-7b-v1.5"   # model name
+        bot_type="completetion" # model type
+        ```
+
+    5. Run the `run.sh` script to start the chatbot.
+
+
     Also, we support to use our finetuned model RecLlama as the backbone language model, the tutorial could be found in [RecLlama](./RecLlama.md).
 
 

InteRecAgent/llm4crs/agent_plan_first_openai.py

@@ -192,6 +192,8 @@ def __init__(
         self.memory = []
 
     def clear(self) -> None:
+        self._shortened_dialogue_history: str = ""
+        self._shortened_dialogue_turn: int = 0
         self.memory = []
 
     def get(self) -> str:
@@ -406,6 +408,7 @@ def clear(self):
         if self._record_planning:
             self._plan_record_cache = {"traj": [], "conv": [], "reward": 0}
         logger.debug("History Cleared!")
+        logger.debug("Memory Cleared!")
         if self.user_profile:
             self.user_profile.clear()
 

InteRecAgent/llm4crs/prompt/system.py

@@ -106,11 +106,11 @@
 You are a conversational {item} recommendation assistant. Your task is to help human find {item}s they are interested in. \
 You would chat with human to mine human interests in {item}s to make it clear what kind of {item}s human is looking for and recommend {item}s to the human when he asks for recommendations. \
 
-Human requests typically fall under chit-chat, {item} info, or {item} recommendations. There are some tools to use to deal with human request.\
+Human requests typically fall under chit-chat, asking for {item} info, or asking for {item} recommendations. There are some tools to use to deal with human request.\
 For chit-chat, respond with your knowledge. For {item} info, use the {LookUpTool}. \
 For special chit-chat, like {item} recommendation reasons, use the {LookUpTool} and your knowledge. \
-For {item} recommendations without information about human preference, chat with human for more information. \
-For {item} recommendations with information for tools, use various tools together. \
+For {item} recommendations without obvious intention, chat with human for more information. \
+For {item} recommendations with information, use various tools to get recommendations. \
 
 To effectively utilize recommendation tools, comprehend human expressions involving profile and intention. \
 Profile encompasses a person's preferences, interests, and behaviors, including gaming history and likes/dislikes. \
@@ -150,8 +150,8 @@
 
 ###
 Question: Do I need to use tools to process human's input?
-Thought: No, I know the final answer.
-Final Answer: the final answer to the original input question
+Thought: No, I do not need to use tools because I know the final answer (or I need to ask more questions).
+Final Answer: the final answer to the original input question (or the question I asked)
 ###
 
 If use tools, use the format:
@@ -161,10 +161,6 @@
 Action: {tool_exe_name}
 Action Input: the input to {tool_exe_name}, should be a plan
 Observation: the result of tool execution
-
-Question: Do I need to use tools to process human's input?
-Thought: No, I know the final answer.
-Final Answer: the final answer to the original input question
 ###
 
 You are allowed to ask some questions instead of using tools to recommend when there is not enough information.

InteRecAgent/llm4crs/prompt/tool.py

@@ -23,7 +23,7 @@
 
 
 LOOK_UP_TOOL_DESC = """
-The tool is used to look up some {item} information in a {item} information table (including statistical information), like number of {item}s, description of {item}s and so on. \
+The tool is used to look up {item}'s detailed information in a {item} information table (including statistical information), like number of {item}s, description of {item}s, price and so on. \
 
 The input of the tools should be a SQL command (in one line) converted from the search query, which would be used to search information in {item} information table. \
 You should try to select as less columns as you can to get the necessary information. \
@@ -36,7 +36,7 @@
 
 
 HARD_FILTER_TOOL_DESC = """
-The tool is a hard condition tool. The tool is useful when human expresses intentions about {item}s with some hard conditions on {item} properties. \
+The tool is a hard-condition {item} filtering tool. The tool is useful when human want {item}s with some hard conditions on {item} properties. \
 The input of the tool should be a one-line SQL SELECT command converted from hard conditions. Here are some rules: \
 1. {item} titles can not be used as conditions in SQL;
 2. the tool can not find similar {item}s;
@@ -49,7 +49,7 @@
 
 
 SOFT_FILTER_TOOL_DESC = """
-The tool is a soft condition filtering tool. \
+The tool is a soft condition {item} filtering tool. \
 The tool can find similar {item}s for specific seed {item}s. \
 Never use this tool if human doesn't express to find some {item}s similar with seed {item}s. \
 There is a similarity score threshold in the tool, only {item}s with similarity above the threshold would be kept. \