Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix index in ChatCompletionChunk (#1648) 

Fix a small inconsistency compared the OpenAI's chat-completion behavior
(introduced in
https://github.com/huggingface/text-generation-inference/pull/1427 cc
@drbh). When using `stream=True`, each chunk has an `index` value in
`ChatCompletionChoice`. This index is not meant to be the index of the
generated token but the index of the choice, which is always 0 (since
TGI always return a single choice).

See https://platform.openai.com/docs/api-reference/chat/object:
> index _integer_
> The index of the choice in the list of choices.

---

So instead of 

```js
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff","choices":[{"index":1,"delta":{"role":"assistant","content":"I"},"logprobs":null,"finish_reason":null}]}
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff","choices":[{"index":2,"delta":{"role":"assistant","content":"'"},"logprobs":null,"finish_reason":null}]}
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff","choices":[{"index":3,"delta":{"role":"assistant","content":"m"},"logprobs":null,"finish_reason":"length"}]}
```

if should return
```js
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff","choices":[{"index":0,"delta":{"role":"assistant","content":"I"},"logprobs":null,"finish_reason":null}]}
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff","choices":[{"index":0,"delta":{"role":"assistant","content":"'"},"logprobs":null,"finish_reason":null}]}
data:{"id":"","object":"text_completion","created":1710508199,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-sha-e6bb3ff","choices":[{"index":0,"delta":{"role":"assistant","content":"m"},"logprobs":null,"finish_reason":"length"}]}
```

**EDIT:** I also edited ToolCall.index to be always `0` (instead of the
generated token index) but for this one I'm actually unsure. It might be
the index of the tool in the array of tools? OpenAI's documentation
doesn't provide any information about it:
> index _integer_

---

I also noticed that in OpenAI's example, the last chunk doesn't have a
delta and is the only one that has a `finish_reason` returning. TGI is
slightly different since the last chunk has both the last delta (i.e.
the last generated token) + the finish reason. I don't think this is
worth fixing since it is not a requirement according to the docs/specs
(at least not that I know of).
This commit is contained in:
Lucain 2024-03-16 17:14:29 +01:00 committed by GitHub
parent 0d9917f744
commit 23fba672e8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
router/src/lib.rs
View File

@ -524,7 +524,6 @@ impl ChatCompletionChunk {
delta: Option<String>,
tool_calls: Option<Vec<String>>,
created: u64,
index: u32,
logprobs: Option<ChatCompletionLogprobs>,
finish_reason: Option<String>,
) -> Self {
@ -535,12 +534,12 @@ impl ChatCompletionChunk {
model,
system_fingerprint,
choices: vec![ChatCompletionChoice {
index,
index: 0,
delta: ChatCompletionDelta {
role: "assistant".to_string(),
content: delta,
tool_calls: tool_calls.map(|tc| DeltaToolCall {
index,
index: 0,
id: String::new(),
r#type: "function".to_string(),
function: Function {

1
router/src/server.rs
View File

@ -895,7 +895,6 @@ async fn chat_completions(
content,
tool_calls,
current_time,
stream_token.index,
logprobs,
stream_token.details.map(|d| d.finish_reason.to_string()),
))