Move clk100k_base tokenizer to docker image (#3411)

### What problem does this PR solve?

Move the tiktoken of cl100k_base into docker image

issue: #3338 

### Type of change

- [x] Refactoring

Signed-off-by: jinhai <haijin.chn@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

Dockerfile

@@ -119,6 +119,9 @@ COPY nltk_data /root/nltk_data
 COPY tika-server-standard-3.0.0.jar tika-server-standard-3.0.0.jar.md5 ./
 ENV TIKA_SERVER_JAR="file:///ragflow/tika-server-standard.jar"
 
+# Copy cl100k_base
+COPY 9b5ad71b2ce5302211f9c61530b329a4922fc6a4 ./
+
 # Copy compiled web pages
 COPY --from=builder /ragflow/web/dist /ragflow/web/dist