github/AutoGPT
1
1
Fork 0
mirror of https://github.com/Significant-Gravitas/AutoGPT.git synced 2026-04-08 03:00:28 -04:00
Code Issues Packages Projects Releases Wiki Activity

Integrate summary memory with autogpt system

Browse Source
This commit is contained in:
Toran Bruce Richards
2023-04-29 23:26:14 +12:00
parent a8cbf51489
commit 4e3035efe4
1 changed files with 47 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
autogpt/llm/chat.py
View File

@@ -12,6 +12,10 @@ from autogpt.logs import logger
from autogpt.memory_management.store_memory import (
save_memory_trimmed_from_context_window,
)
from autogpt.memory_management.summary_memory import (
get_newly_trimmed_messages,
update_running_summary,
)
cfg = Config()
@@ -36,10 +40,10 @@ def generate_context(prompt, relevant_memory, full_message_history, model):
create_chat_message(
"system", f"The current time and date is {time.strftime('%c')}"
),
create_chat_message(
"system",
f"This reminds you of these events from your past:\n{relevant_memory}\n\n",
),
# create_chat_message(
# "system",
# f"This reminds you of these events from your past:\n{relevant_memory}\n\n",
# ),
]
# Add messages from the full message history until we reach the token limit
@@ -81,21 +85,21 @@ def chat_with_ai(
"""
model = cfg.fast_llm_model # TODO: Change model from hardcode to argument
# Reserve 1000 tokens for the response
logger.debug(f"Token limit: {token_limit}")
send_token_limit = token_limit - 1000
if len(full_message_history) == 0:
relevant_memory = ""
else:
recent_history = full_message_history[-5:]
shuffle(recent_history)
relevant_memories = permanent_memory.get_relevant(
str(recent_history), 5
)
if relevant_memories:
shuffle(relevant_memories)
relevant_memory = str(relevant_memories)
# if len(full_message_history) == 0:
# relevant_memory = ""
# else:
# recent_history = full_message_history[-5:]
# shuffle(recent_history)
# relevant_memories = permanent_memory.get_relevant(
# str(recent_history), 5
# )
# if relevant_memories:
# shuffle(relevant_memories)
# relevant_memory = str(relevant_memories)
relevant_memory = ""
logger.debug(f"Memory Stats: {permanent_memory.get_stats()}")
(
@@ -105,33 +109,37 @@ def chat_with_ai(
current_context,
) = generate_context(prompt, relevant_memory, full_message_history, model)
while current_tokens_used > 2500:
# remove memories until we are under 2500 tokens
relevant_memory = relevant_memory[:-1]
(
next_message_to_add_index,
current_tokens_used,
insertion_index,
current_context,
) = generate_context(
prompt, relevant_memory, full_message_history, model
)
# while current_tokens_used > 2500:
# # remove memories until we are under 2500 tokens
# relevant_memory = relevant_memory[:-1]
# (
# next_message_to_add_index,
# current_tokens_used,
# insertion_index,
# current_context,
# ) = generate_context(
# prompt, relevant_memory, full_message_history, model
# )
current_tokens_used += count_message_tokens(
[create_chat_message("user", user_input)], model
) # Account for user input (appended later)
current_tokens_used += 500 # Account for memory (appended later) TODO: The final memory may be less than 500 tokens
# Add Messages until the token limit is reached or there are no more messages to add.
while next_message_to_add_index >= 0:
# print (f"CURRENT TOKENS USED: {current_tokens_used}")
message_to_add = full_message_history[next_message_to_add_index]
tokens_to_add = count_message_tokens([message_to_add], model)
if current_tokens_used + tokens_to_add > send_token_limit:
save_memory_trimmed_from_context_window(
full_message_history,
next_message_to_add_index,
permanent_memory,
)
# save_memory_trimmed_from_context_window(
# full_message_history,
# next_message_to_add_index,
# permanent_memory,
# )
break
# Add the most recent message to the start of the current context,
@@ -146,6 +154,12 @@ def chat_with_ai(
# Move to the next most recent message in the full message history
next_message_to_add_index -= 1
# Insert Memories
newly_trimmed_messages = get_newly_trimmed_messages(full_message_history=full_message_history, current_context=current_context)
memory = update_running_summary(newly_trimmed_messages)
current_context.insert(insertion_index, memory)
api_manager = ApiManager()
# inform the AI about its remaining budget (if it has one)
if api_manager.get_total_budget() > 0.0: