Returned VLM chat sample in CI. (#935)

Returned VLM chat sample in CI.

Author: popovaan

.github/workflows/causal_lm_cpp.yml

@@ -701,7 +701,7 @@ jobs:
         run: |
           source ./ov/setupvars.sh
           cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
-          cmake --build ./build/ --config Release --target visual_language_chat -j
+          cmake --build ./build/ --config Release --target visual_language_chat py_generate_pipeline -j
       - name: Download and convert a model and an image
         run: |
           source ./ov/setupvars.sh
@@ -716,6 +716,13 @@ jobs:
           && timeout 120s ./build/samples/cpp/visual_language_chat/visual_language_chat ./miniCPM-V-2_6/ cat.jpg
           <<< $'What is on the image?\nWhat is special on the image?'
 
+      - name: Run python chat sample
+        run: |
+          source ./ov/setupvars.sh
+          export PYTHONPATH=./build/:$PYTHONPATH
+          printf 'What is on the image?\nWhat is special on the image?\n' > ./input.txt
+          timeout 120s python ./samples/python/visual_language_chat/visual_language_chat.py ./miniCPM-V-2_6/ cat.jpg < input.txt > ./pred.txt
+
   cpp-continuous-batching-ubuntu:
     runs-on: ubuntu-20.04-8-cores
     defaults:

samples/python/vlm_chat_sample/README.md renamed to samples/python/visual_language_chat/README.md

@@ -16,7 +16,7 @@ pip install --upgrade-strategy eager -r ../../requirements.txt
 ## Run:
 [This image](https://github.com/openvinotoolkit/openvino_notebooks/assets/29454499/d5fbbd1a-d484-415c-88cb-9986625b7b11) can be used as a sample image.
 
-`vlm_chat_sample.py ./miniCPM-V-2_6/ 319483352-d5fbbd1a-d484-415c-88cb-9986625b7b11.jpg`
+`visual_language_chat.py ./miniCPM-V-2_6/ 319483352-d5fbbd1a-d484-415c-88cb-9986625b7b11.jpg`
 
 
 Discrete GPUs (dGPUs) usually provide better performance compared to CPUs. It is recommended to run larger models on a dGPU with 32GB+ RAM. # TODO: examples of larger models

samples/python/vlm_chat_sample/vlm_chat_sample.py renamed to samples/python/visual_language_chat/visual_language_chat.py

@@ -54,12 +54,16 @@ def main():
     config.max_new_tokens = 100
 
     pipe.start_chat()
+    prompt = input('question:\n')
+    pipe(prompt, image=image, generation_config=config, streamer=streamer)
+    print('\n----------')
+
     while True:
         try:
             prompt = input('question:\n')
         except EOFError:
             break
-        pipe(prompt, image=image, generation_config=config, streamer=streamer)
+        pipe(prompt, generation_config=config, streamer=streamer)
         print('\n----------')
     pipe.finish_chat()