mirror of
https://github.com/cpacker/MemGPT.git
synced 2025-06-03 04:30:22 +00:00
17c5e3a0bc
* I added some json repairs that helped me with malformed messages There are two of them: The first will remove hard line feeds that appear in the message part because the model added those instead of escaped line feeds. This happens a lot in my experiments and that actually fixes them. The second one is less tested and should handle the case that the model answers with multiple blocks of strings in quotes or even uses unescaped quotes. It should grab everything betwenn the message: " and the ending curly braces, escape them and makes it propper json that way. Disclaimer: Both function were written with the help of ChatGPT-4 (I can't write much Python). I think the first one is quite solid but doubt that the second one is fully working. Maybe somebody with more Python skills than me (or with more time) has a better idea for this type of malformed replies. * Moved the repair output behind the debug flag and removed the "clean" one * Added even more fixes (out of what I just encountered while testing) It seems that cut of json can be corrected and sometimes the model is to lazy to add not just one curly brace but two. I think it does not "cost" a lot to try them all out. But the expeptions get massive that way :) * black * for the final hail mary with extract_first_json, might as well add a double end bracket instead of single --------- Co-authored-by: cpacker <packercharles@gmail.com>
65 lines
1.6 KiB
Python
65 lines
1.6 KiB
Python
import json
|
|
|
|
import memgpt.local_llm.json_parser as json_parser
|
|
|
|
|
|
EXAMPLE_MISSING_CLOSING_BRACE = """{
|
|
"function": "send_message",
|
|
"params": {
|
|
"inner_thoughts": "Oops, I got their name wrong! I should apologize and correct myself.",
|
|
"message": "Sorry about that! I assumed you were Chad. Welcome, Brad! "
|
|
}
|
|
"""
|
|
|
|
EXAMPLE_BAD_TOKEN_END = """{
|
|
"function": "send_message",
|
|
"params": {
|
|
"inner_thoughts": "Oops, I got their name wrong! I should apologize and correct myself.",
|
|
"message": "Sorry about that! I assumed you were Chad. Welcome, Brad! "
|
|
}
|
|
}<|>"""
|
|
|
|
EXAMPLE_DOUBLE_JSON = """{
|
|
"function": "core_memory_append",
|
|
"params": {
|
|
"name": "human",
|
|
"content": "Brad, 42 years old, from Germany."
|
|
}
|
|
}
|
|
{
|
|
"function": "send_message",
|
|
"params": {
|
|
"message": "Got it! Your age and nationality are now saved in my memory."
|
|
}
|
|
}
|
|
"""
|
|
|
|
EXAMPLE_HARD_LINE_FEEDS = """{
|
|
"function": "send_message",
|
|
"params": {
|
|
"message": "Let's create a list:
|
|
- First, we can do X
|
|
- Then, we can do Y!
|
|
- Lastly, we can do Z :)"
|
|
}
|
|
}
|
|
"""
|
|
|
|
|
|
def test_json_parsers():
|
|
"""Try various broken JSON and check that the parsers can fix it"""
|
|
|
|
test_strings = [EXAMPLE_MISSING_CLOSING_BRACE, EXAMPLE_BAD_TOKEN_END, EXAMPLE_DOUBLE_JSON, EXAMPLE_HARD_LINE_FEEDS]
|
|
|
|
for string in test_strings:
|
|
try:
|
|
json.loads(string)
|
|
assert False, f"Test JSON string should have failed basic JSON parsing:\n{string}"
|
|
except:
|
|
print("String failed (expectedly)")
|
|
try:
|
|
json_parser.clean_json(string)
|
|
except:
|
|
f"Failed to repair test JSON string:\n{string}"
|
|
raise
|