JSONDecodeError: AI sometimes produces JSON with a code block format

[FoliageOwO]

🐛 Describe the bug

I was creating a memory, following the official document.

But I did get confused at this error:

json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

which is occurred at the line

new_memories_with_actions = json.loads(new_memories_with_actions)

After checking what on earth are the new_memories_with_actions, I found that the AI did respond a JSON content, but with triple backticks (the code block format), just like this (I'm using diff because the triple backticks will not show at the time):

+ ```json
+ {
+     "memory": [
+         {
+             "id": "(UUID)",
+             "text": "I'm visiting Paris",
+             "event": "ADD"
+         }
+     ]
+ }
+ ```

which surely will get json.loads() crashed.

Is anything wrong?

EDIT:
BTW I think it was the model that caused the issue of generating bad content, so I need to declare that I was using Qwen (the model by Alibaba Cloud), not gpt-4 or gpt-4o or something that was mentioned in the official document.

[FoliageOwO]

I solved this problem by adding these lines in mem0/memory/main.py:

mem0/mem0/memory/main.py

Lines 168 to 173 in f40a2e7

	function_calling_prompt = get_update_memory_messages(retrieved_old_memory, new_retrieved_facts)
	new_memories_with_actions = self.llm.generate_response(
	messages=[{"role": "user", "content": function_calling_prompt}],
	response_format={"type": "json_object"},
	)
	new_memories_with_actions = json.loads(new_memories_with_actions)

  ...
+ import re
  ...
          function_calling_prompt = get_update_memory_messages(retrieved_old_memory, new_retrieved_facts)
          new_memories_with_actions = self.llm.generate_response(
              messages=[{"role": "user", "content": function_calling_prompt}],
              response_format={"type": "json_object"},
          )
    
+         search_result = re.search("(```json)((.*\n)+)(```)", new_memories_with_actions)
+         if search_result:
+             new_memories_with_actions = search_result.group(2).strip()

          new_memories_with_actions = json.loads(new_memories_with_actions)

EDIT:
The issue will not occur only at the json.loads() line I mentioned before, but also here:

mem0/mem0/memory/main.py

Lines 142 to 145 in f40a2e7

	response = self.llm.generate_response(
	messages=[{"role": "system", "content": system_prompt}, {"role": "user", "content": user_prompt}],
	response_format={"type": "json_object"},
	)

[prateekchhikara]

@FoliageOwO can you please raise a PR for this?

[FoliageOwO]

@FoliageOwO can you please raise a PR for this?

@prateekchhikara Hi, I just created a new PR #1860, please review it when you get a second.

[hhhhhge]

@FoliageOwO can you please raise a PR for this?

@prateekchhikara Hi, I just created a new PR #1860, please review it when you get a second.

When will this bug be fixed o(╥﹏╥)o

[FoliageOwO]

@hhhhhge 等 PR 被合并并发布到新的 Release 版本后，所有人就都可以用上了。如果你目前要紧急解决这个问题的话，可以手动克隆我的 fork 仓库到 pip 安装的包的目录，也可以根据我的 commit 手动修改本地包源码。目前的 PR 并能代表最终 Release，我的方案可能不是最好的，也许可能会被其他贡献者改进，但是可以暂时用来应急。

For those who can't wait for the PR approval and releasing process: you can clone my fork repository to your pip packages folder, or manually edit local mem0 source codes according to my commit.