feat(tokens.py): add function to count number of tokens used by a list of messages

utils/tokens.py

@@ -0,0 +1,27 @@
+import tiktoken
+
+async def num_tokens_from_messages(messages, model="gpt-3.5-turbo"):
+    """Returns the number of tokens used by a list of messages."""
+    try:
+        encoding = tiktoken.encoding_for_model(model)
+    except KeyError:
+        print("Warning: model not found. Using cl100k_base encoding.")
+        encoding = tiktoken.get_encoding("cl100k_base")
+
+    if model.startswith("gpt-3.5-turbo"):
+        tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
+        tokens_per_name = -1  # if there's a name, the role is omitted
+    elif model.startswith("gpt-4"):
+        tokens_per_message = 3
+        tokens_per_name = 1
+    else:
+        raise NotImplementedError(f"""num_tokens_from_messages() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens.""")
+    num_tokens = 0
+    for message in messages:
+        num_tokens += tokens_per_message
+        for key, value in message.items():
+            num_tokens += len(encoding.encode(value))
+            if key == "name":
+                num_tokens += tokens_per_name
+    num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
+    return num_tokens