Skip to content

adding missing args in create_completion for functionary chat handler #1430

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 8, 2024
Merged

adding missing args in create_completion for functionary chat handler #1430

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions llama_cpp/llama_chat_format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2322,7 +2322,7 @@ def generate_streaming(tools, functions, function_call, prompt):
prompt = prompt
stops = ["\n", END_ASSISTANT_TOKEN]

completion = create_completion(stop=stops)
completion = create_completion(prompt=prompt, stop=stops, grammar=grammar)
completion_text = completion["choices"][0]["text"]
completion_tokens += completion["usage"]["completion_tokens"]

Expand All @@ -2349,7 +2349,7 @@ def generate_streaming(tools, functions, function_call, prompt):
completion_text.split(START_FUNCTION_CALL_TOKEN)[-1][:-1].strip()
)
grammar = get_grammar(function_calls[-1])
completion = create_completion(stop=END_FUNCTION_CALL_TOKEN)
completion = create_completion(prompt=prompt, stop=END_FUNCTION_CALL_TOKEN, grammar=grammar)
completion_tokens += completion["usage"]["completion_tokens"]
function_bodies.append(completion["choices"][0]["text"].strip())
# If the prompt involves a function call, just append generated parameters to function_bodies
Expand All @@ -2363,7 +2363,7 @@ def generate_streaming(tools, functions, function_call, prompt):
function_calls.append(function_call)
grammar = get_grammar(function_call)
stops = [STOP_TOKEN, FROM_TOKEN]
completion = create_completion(stop=stops)
completion = create_completion(prompt=prompt, stop=stops, grammar=grammar)
completion_text = completion["choices"][0]["text"]
completion_tokens += completion["usage"]["completion_tokens"]
function_bodies.append(completion_text.strip())
Expand All @@ -2373,7 +2373,7 @@ def generate_streaming(tools, functions, function_call, prompt):
# Generate function name first
grammar = None
stops = CONTENT_TOKEN
completion = create_completion(stop=stops)
completion = create_completion(prompt=prompt, stop=stops, grammar=grammar)
completion_text = completion["choices"][0]["text"]
completion_tokens += completion["usage"]["completion_tokens"]
function_name = completion_text.strip()
Expand All @@ -2386,7 +2386,7 @@ def generate_streaming(tools, functions, function_call, prompt):
grammar = get_grammar(function_call)
# Generate content
stops = [RECIPIENT_TOKEN, STOP_TOKEN]
completion = create_completion(stop=stops)
completion = create_completion(prompt=prompt, stop=stops, grammar=grammar)
completion_text = completion["choices"][0]["text"]
completion_tokens += completion["usage"]["completion_tokens"]
if function_name == "all":
Expand All @@ -2413,7 +2413,7 @@ def generate_streaming(tools, functions, function_call, prompt):
# Check whether the model wants to generate another turn
prompt += completion_text.strip()
grammar = None
completion = create_completion(stop=stops)
completion = create_completion(prompt=prompt, stop=stops, grammar=grammar)
completion_tokens += completion["usage"]["completion_tokens"]
if "<|from|> assistant" in completion["choices"][0]["text"] or "<|from|>assistant" in completion["choices"][0]["text"]:
prompt += "\n<|from|>assistant\n<|recipient|>"
Expand Down Expand Up @@ -3564,4 +3564,4 @@ def chatml_function_calling(
},
}

raise ValueError("Automatic streaming tool choice is not supported")
raise ValueError("Automatic streaming tool choice is not supported")