add fixes

app.py

@@ -216,13 +216,14 @@ def http_bot(state, model_selector, temperature, top_p, max_new_tokens, request:
 
     # Construct prompt
     prompt = state.get_prompt()
-
+    dir_path = "./"
     all_images = state.get_images(return_pil=True)
     all_image_hash = [hashlib.md5(image.tobytes()).hexdigest() for image in all_images]
     for image, hash in zip(all_images, all_image_hash):
         t = datetime.datetime.now()
-        dir_path = os.path.join(LOGDIR, "serve_images", f"{t.year}-{t.month:02d}-{t.day:02d}")
+        # dir_path = os.path.join(LOGDIR, "serve_images", f"{t.year}-{t.month:02d}-{t.day:02d}")
         # filename = os.path.join(LOGDIR, "serve_images", f"{t.year}-{t.month:02d}-{t.day:02d}", f"{hash}.jpg")
+        # filename = os.path.join(dir_path, f"{hash}.jpg")
         filename = os.path.join(dir_path, f"{hash}.jpg")
         if not os.path.isfile(filename):
             os.makedirs(os.path.dirname(filename), exist_ok=True)
@@ -251,7 +252,7 @@ def http_bot(state, model_selector, temperature, top_p, max_new_tokens, request:
         #     headers=headers, json=pload, stream=True, timeout=10)
         stop = state.sep if state.sep_style in [SeparatorStyle.SINGLE, SeparatorStyle.MPT] else state.sep2
         #TODO: define inference and run function
-        results, extracted_texts = inference_and_run(
+        extracted_texts = inference_and_run(
         image_path=filename, # double check this
         image_dir=dir_path,
         prompt=prompt,
@@ -264,19 +265,27 @@ def http_bot(state, model_selector, temperature, top_p, max_new_tokens, request:
         )
         response = extracted_texts
         logger.info(f"This is the respone {response}")
-        for chunk in response.iter_lines(decode_unicode=False, delimiter=b"\0"):
-            if chunk:
-                data = json.loads(chunk.decode())
-                if data["error_code"] == 0:
-                    output = data["text"][len(prompt):].strip()
-                    state.messages[-1][-1] = output + "▌"
-                    yield (state, state.to_gradio_chatbot()) + (disable_btn,) * 5
-                else:
-                    output = data["text"] + f" (error_code: {data['error_code']})"
-                    state.messages[-1][-1] = output
-                    yield (state, state.to_gradio_chatbot()) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn)
-                    return
-                time.sleep(0.03)
+        delay=0.01
+        # for chunk in response.iter_lines(decode_unicode=False, delimiter=b"\0"):
+        #     if chunk:
+        #         data = json.loads(chunk.decode())
+        #         if data["error_code"] == 0:
+        #             output = data["text"][len(prompt):].strip()
+        #             state.messages[-1][-1] = output + "▌"
+        #             yield (state, state.to_gradio_chatbot()) + (disable_btn,) * 5
+        #         else:
+        #             output = data["text"] + f" (error_code: {data['error_code']})"
+        #             state.messages[-1][-1] = output
+        #             yield (state, state.to_gradio_chatbot()) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn)
+        #             return
+        #         time.sleep(0.03)
+        text = response[0]
+        output = ""  # Will hold the progressively built output
+        for i, char in enumerate(text):
+            output += char
+            state.messages[-1][-1] = output + "▌"  # Add cursor ▌ at the end
+            yield (state, state.to_gradio_chatbot()) + (disable_btn,) * 5
+            time.sleep(delay)  # Control typing speed with delay
     except requests.exceptions.RequestException as e:
         state.messages[-1][-1] = server_error_msg
         yield (state, state.to_gradio_chatbot()) + (disable_btn, disable_btn, disable_btn, enable_btn, enable_btn)

eval.json

@@ -1 +1 @@
-[{"id": 0, "image": "8b23f327b90b6211049acd36e3f99975.jpg", "image_h": 433, "image_w": 400, "conversations": [{"from": "human", "value": "<image>\nA chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.<start_of_turn>user\n<image>\ndescribe the image in details<end_of_turn>\n<start_of_turn>model\n"}]}]
+[{"id": 0, "image": "8b23f327b90b6211049acd36e3f99975.jpg", "image_h": 433, "image_w": 400, "conversations": [{"from": "human", "value": "<image>\nA chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.<start_of_turn>user\n<image>\nexplain what you see<end_of_turn>\n<start_of_turn>model\n"}]}]

eval_output.jsonl/0_of_1.jsonl

@@ -0,0 +1 @@
+{"id": 0, "image_path": "8b23f327b90b6211049acd36e3f99975.jpg", "prompt": "A chat between a human and an AI that understands visuals. In images, [x, y] denotes points: top-left [0, 0], bottom-right [width-1, height-1]. Increasing x moves right; y moves down. Bounding box: [x1, y1, x2, y2]. Image size: 1000x1000. Follow instructions.<start_of_turn>user", "text": "A chat between a human and an unknown entity. \n\nThe conversation starts with a message from Jackyline Herrera saying, \"Ask Jackie to borrow her truck\". The reply is, \"Get gravel for bow, walk, 10, 1, 1, Shopping List\". \n\nThe next message is from Get Gravel for the truck, and the reply is, \"Buy mulch, #shoppinglist\". \n\nThe third message is from Buy mulch for the garden, and the reply is, \"Pick up succulents\". \n\nThe fourth message is from Pick up succulents for the garden, and the reply is, \"Buy soil for succulents\". \n\nThe fifth message is from Buy soil for succulents, and the reply is, \"Pick up soil for succulents\". \n\nThe sixth message is from Pick up succulents for the garden, and the reply is, \"Pick up soil for succulents\". \n\nThe seventh message is from Pick up succulents for the garden, and the reply is, \"Pick up soil for succulents\". \n\nThe eighth message is from Pick up succulents for the garden, and the reply is, \"Pick up soil for succulents\". \n\nThe ninth message is from Pick up succulents for the garden, and the reply is, \"Look up native vegetables along the fence\". \n\nThe tenth message is from Shopping List, and the reply is, \"Shopping List\". \n\nThe message at the bottom is from Shopping List, and the reply is, \"Look up native vegetables along the fence\". \n\nThe message at the very bottom is from Shopping List, and the reply is, \"Looking: Fran\".", "label": null}