starting to work

Dockerfile

@@ -16,6 +16,7 @@ RUN pip3 install --no-cache-dir -r requirements.txt
 # Copy the current directory contents into the container at /app
 COPY scripts /app/scripts
 COPY swarms /app/swarms
+COPY example.py /app/example.py
 
 # Make port 80 available to the world outside this container
 EXPOSE 80

swarms/models/__init__.py

@@ -1,77 +1,77 @@
 from swarms.models.base_embedding_model import BaseEmbeddingModel
 from swarms.models.base_llm import BaseLLM  # noqa: E402
-from swarms.models.base_multimodal_model import BaseMultiModalModel
-from swarms.models.fuyu import Fuyu  # noqa: E402
-from swarms.models.gpt4_vision_api import GPT4VisionAPI  # noqa: E402
-from swarms.models.huggingface import HuggingfaceLLM  # noqa: E402
-from swarms.models.idefics import Idefics  # noqa: E402
-from swarms.models.kosmos_two import Kosmos  # noqa: E402
-from swarms.models.layoutlm_document_qa import LayoutLMDocumentQA
-from swarms.models.llava import LavaMultiModal  # noqa: E402
+#from swarms.models.base_multimodal_model import BaseMultiModalModel
+#from swarms.models.fuyu import Fuyu  # noqa: E402
+#from swarms.models.gpt4_vision_api import GPT4VisionAPI  # noqa: E402
+#from swarms.models.huggingface import HuggingfaceLLM  # noqa: E402
+#from swarms.models.idefics import Idefics  # noqa: E402
+#from swarms.models.kosmos_two import Kosmos  # noqa: E402
+#from swarms.models.layoutlm_document_qa import LayoutLMDocumentQA
+#from swarms.models.llava import LavaMultiModal  # noqa: E402
 
-from swarms.models.nougat import Nougat  # noqa: E402
-from swarms.models.palm import GooglePalm as Palm  # noqa: E402
-from swarms.models.openai_tts import OpenAITTS  # noqa: E402
-from swarms.models.popular_llms import Anthropic as Anthropic
-from swarms.models.popular_llms import (
-    AzureOpenAILLM as AzureOpenAI,
-)
-from swarms.models.popular_llms import (
-    CohereChat as Cohere,
-)
+#from swarms.models.nougat import Nougat  # noqa: E402
+#from swarms.models.palm import GooglePalm as Palm  # noqa: E402
+#from swarms.models.openai_tts import OpenAITTS  # noqa: E402
+#from swarms.models.popular_llms import Anthropic as Anthropic
+# from swarms.models.popular_llms import (
+#     AzureOpenAILLM as AzureOpenAI,
+# )
+# from swarms.models.popular_llms import (
+#     CohereChat as Cohere,
+# )
 from swarms.models.popular_llms import (
     OpenAIChatLLM as OpenAIChat,
 )
 from swarms.models.popular_llms import (
     OpenAILLM as OpenAI,
 )
-from swarms.models.popular_llms import OctoAIChat
-from swarms.models.qwen import QwenVLMultiModal  # noqa: E402
-from swarms.models.popular_llms import ReplicateChat as Replicate
-from swarms.models.sampling_params import SamplingParams, SamplingType
-from swarms.models.together import TogetherLLM  # noqa: E402
+# from swarms.models.popular_llms import OctoAIChat
+# from swarms.models.qwen import QwenVLMultiModal  # noqa: E402
+# from swarms.models.popular_llms import ReplicateChat as Replicate
+# from swarms.models.sampling_params import SamplingParams, SamplingType
+# from swarms.models.together import TogetherLLM  # noqa: E402
 from swarms.models.types import (  # noqa: E402
-    AudioModality,
-    ImageModality,
-    MultimodalData,
+#    AudioModality,
+#    ImageModality,
+#    MultimodalData,
     TextModality,
-    VideoModality,
+#    VideoModality,
 )
-from swarms.models.vilt import Vilt  # noqa: E402
-from swarms.models.openai_embeddings import OpenAIEmbeddings
-from swarms.models.llama3_hosted import llama3Hosted
+#from swarms.models.vilt import Vilt  # noqa: E402
+#from swarms.models.openai_embeddings import OpenAIEmbeddings
+#from swarms.models.llama3_hosted import llama3Hosted
 
-__all__ = [
-    "BaseEmbeddingModel",
-    "BaseLLM",
-    "BaseMultiModalModel",
-    "Fuyu",
-    "GPT4VisionAPI",
-    "HuggingfaceLLM",
-    "Idefics",
-    "Kosmos",
-    "LayoutLMDocumentQA",
-    "LavaMultiModal",
-    "Nougat",
-    "Palm",
-    "OpenAITTS",
-    "Anthropic",
-    "AzureOpenAI",
-    "Cohere",
-    "OpenAIChat",
-    "OpenAI",
-    "OctoAIChat",
-    "QwenVLMultiModal",
-    "Replicate",
-    "SamplingParams",
-    "SamplingType",
-    "TogetherLLM",
-    "AudioModality",
-    "ImageModality",
-    "MultimodalData",
-    "TextModality",
-    "VideoModality",
-    "Vilt",
-    "OpenAIEmbeddings",
-    "llama3Hosted",
-]
+# __all__ = [
+#     "BaseEmbeddingModel",
+#     "BaseLLM",
+# #    "BaseMultiModalModel",
+# #    "Fuyu",
+# #    "GPT4VisionAPI",
+# #    "HuggingfaceLLM",
+# #    "Idefics",
+# #    "Kosmos",
+# #    "LayoutLMDocumentQA",
+# #    "LavaMultiModal",
+#     "Nougat",
+#     "Palm",
+#     "OpenAITTS",
+#     "Anthropic",
+#     "AzureOpenAI",
+#     "Cohere",
+#     "OpenAIChat",
+#     "OpenAI",
+#     "OctoAIChat",
+#     "QwenVLMultiModal",
+#     "Replicate",
+#     "SamplingParams",
+#     "SamplingType",
+#     "TogetherLLM",
+#     "AudioModality",
+#     "ImageModality",
+#     "MultimodalData",
+#     "TextModality",
+#     "VideoModality",
+#     "Vilt",
+#     "OpenAIEmbeddings",
+#     "llama3Hosted",
+# ]

swarms/structs/agent.py

@@ -718,7 +718,7 @@ class Agent(BaseStructure):
             loop_count = 0
 
             # Clear the short memory
-            # response = None
+            response = "ERROR"
 
             while self.max_loops == "auto" or loop_count < self.max_loops:
                 loop_count += 1

swarms/tools/logits_processor.py

@@ -1,4 +1,4 @@
-import torch
+#import torch
 from transformers import (
     LogitsWarper,
     PreTrainedTokenizer,
@@ -13,7 +13,7 @@ class StringStoppingCriteria(StoppingCriteria):
 
     def __call__(
         self,
-        input_ids: torch.LongTensor,
+        input_ids,
         _,
     ) -> bool:
         if len(input_ids[0]) <= self.prompt_length:
@@ -42,8 +42,8 @@ class NumberStoppingCriteria(StoppingCriteria):
 
     def __call__(
         self,
-        input_ids: torch.LongTensor,
-        scores: torch.FloatTensor,
+        input_ids,
+        scores,
     ) -> bool:
         decoded = self.tokenizer.decode(
             input_ids[0][self.prompt_length :],
@@ -74,7 +74,7 @@ class OutputNumbersTokens(LogitsWarper):
         self.tokenizer = tokenizer
         self.tokenized_prompt = tokenizer(prompt, return_tensors="pt")
         vocab_size = len(tokenizer)
-        self.allowed_mask = torch.zeros(vocab_size, dtype=torch.bool)
+        #self.allowed_mask = torch.zeros(vocab_size, dtype=torch.bool)
 
         for _, token_id in tokenizer.get_vocab().items():
             token_str = tokenizer.decode(token_id).strip()