Support Chinese for Docsum (#960)

Signed-off-by: Xinyao Wang <xinyao.wang@intel.com>
This commit is contained in:
XinyaoWa
2024-10-17 14:58:21 +08:00
committed by GitHub
parent eeced9b31c
commit b0f7c9cfc2
3 changed files with 9 additions and 3 deletions

View File

@@ -124,7 +124,7 @@ docker compose up -d
```bash
curl http://${host_ip}:8888/v1/docsum -H "Content-Type: application/json" -d '{
"messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
"messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5.","max_tokens":32, "language":"en", "stream":false
}'
```

View File

@@ -115,7 +115,7 @@ docker compose up -d
```bash
curl http://${host_ip}:8888/v1/docsum -H "Content-Type: application/json" -d '{
"messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."
"messages": "Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5.","max_tokens":32, "language":"en", "stream":false
}'
```