fixed bugs and update requirements file

Author: Vamsi-Kommineni

Code/mixtral/NER.py

@@ -13,11 +13,11 @@ def NER_mixtral(config):
         Answer:::
         '''
         for i in [2,5,6,4,12,15,13,22,17,19,20,8,25]:
-        Answer = read_txt(f"{config.get('Paths', 'Ans_to_cq_output_folder')}Publication{pub}_CQ{i}.txt")
-        prompt = f"Q: {CQs[i-1]}\nA: {Answer}\n"
-        combined_prompt += prompt
-        combined_prompt +=Answer_format
-        #print(combined_prompt)
-        output = llm.invoke(combined_prompt)
-        with open(f"{config.get('Paths', 'NER_mixtral_save')}Publication{pub}_concepts.txt", 'w') as f:
-            f.write(output)
+            Answer = read_txt(f"{config.get('Paths', 'Ans_to_cq_output_folder')}Publication{pub}_CQ{i}.txt")
+            prompt = f"Q: {CQs[i-1]}\nA: {Answer}\n"
+            combined_prompt += prompt
+            combined_prompt +=Answer_format
+            #print(combined_prompt)
+            output = llm.invoke(combined_prompt)
+            with open(f"{config.get('Paths', 'NER_mixtral_save')}Publication{pub}_concepts.txt", 'w') as f:
+                f.write(output)

Code/mixtral/Ontology_creation.py

@@ -23,7 +23,7 @@ def Ontology_creation(config):
     inverse_properties = content[inverse_properties_s_ind:].strip()
     base_onto_class, base_onto_property = get_base_onto_class(config.get('Paths', 'SOTAOntology_path'))
 
-    prompt = prompt_template.format(concepts=concepts,relations=relationships,base_onto_class=base_onto_class,base_onto_property=base_onto_property)
+    prompt = prompt_template.format(concepts=concepts,relations=relationships,data_properties=data_properties,InverseProperties=inverse_properties,base_onto_class=base_onto_class,base_onto_property=base_onto_property)
 
     with open(config.get('Paths', 'Created_onto_path'),"w") as f:
         f.write(llm.invoke(prompt))

Code/mixtral/RAG_CQ_answering_with_LLMs.py

@@ -25,5 +25,5 @@ def RAG_CQ_answering(config):
             prompt = prompt_template.format(query=cq)
             result = chain({"query": prompt}, return_only_outputs=True)
             wrapped_text = textwrap.fill(result['result'], width=100)
-            with open(f"{config.get('Paths', 'Ans_to_cq_path')}Publication{d}_CQ{p}.txt", 'w') as f:
+            with open(f"{config.get('Paths', 'Ans_to_cq_input_folder')}Publication{d}_CQ{p}.txt", 'w') as f:
                 f.write(wrapped_text)

README.md

@@ -23,7 +23,7 @@ The repository encompasses various components, including code for data preproces
 Add the Hugging face access token in the helper_functions.py in the following line:
 access_token_read = os.getenv('access_token_read_hf')  
 
-Install the prerequisite using the requirements.txt file. 
+Create virtual environment and install the prerequisite using the requirements.txt file. The code (v2.0.1) was tested & reproduced using Python 3.10.16 on a Linux system.
 
 To run the whole pipeline, submit (execute) your job using main.py and use config.ini to customise the variables and paths 
 

requirements.txt

@@ -1,25 +1,26 @@
-accelerate==0.25.0
-aiohttp==3.10.11
+accelerate==1.3.0
+aiohttp==3.9.1
 aioprometheus==23.12.0
 aiosignal==1.3.1
 annotated-types==0.6.0
 antlr4-python3-runtime==4.9.3
 anyio==4.2.0
 appdirs==1.4.4
 asttokens==2.4.1
+async-timeout==4.0.3
 attrs==23.1.0
 backoff==2.2.1
 beautifulsoup4==4.12.2
 bitsandbytes==0.41.3.post2
-certifi==2024.7.4
+certifi==2023.11.17
 cffi==1.16.0
 chardet==5.2.0
 charset-normalizer==3.3.2
 click==8.1.7
 coloredlogs==15.0.1
 comm==0.2.1
 contourpy==1.2.0
-cryptography==43.0.1
+cryptography==41.0.7
 cupy-cuda12x==12.1.0
 cycler==0.12.1
 dataclasses-json==0.6.3
@@ -32,6 +33,7 @@ distro==1.9.0
 effdet==0.4.1
 einops==0.7.0
 emoji==2.9.0
+exceptiongroup==1.2.2
 executing==2.0.1
 faiss-cpu==1.7.4
 fastapi==0.109.2
@@ -47,15 +49,15 @@ h11==0.14.0
 httpcore==1.0.3
 httptools==0.6.1
 httpx==0.26.0
-huggingface-hub==0.20.1
+huggingface-hub==0.28.1
 humanfriendly==10.0
-idna==3.7
+idna==3.6
 iopath==0.1.10
 ipykernel==6.29.0
 ipython==8.20.0
 isodate==0.6.1
 jedi==0.19.1
-Jinja2==3.1.5
+Jinja2==3.1.2
 joblib==1.3.2
 jsonpatch==1.33
 jsonpath-python==1.0.6
@@ -65,9 +67,9 @@ jsonschema-specifications==2023.12.1
 jupyter_client==8.6.0
 jupyter_core==5.7.1
 kiwisolver==1.4.5
-langchain-community==0.2.19
-langchain==0.3.0
-langchain-core==0.1.35
+langchain==0.0.352
+langchain-community==0.0.5
+langchain-core==0.1.23
 langchain-openai==0.0.6
 langdetect==1.0.9
 langsmith==0.0.87
@@ -85,7 +87,7 @@ mypy-extensions==1.0.0
 nest-asyncio==1.6.0
 networkx==3.2.1
 ninja==1.11.1.1
-nltk==3.9
+nltk==3.8.1
 numpy==1.26.2
 nvidia-cublas-cu12==12.1.3.1
 nvidia-cuda-cupti-cu12==12.1.105
@@ -100,11 +102,11 @@ nvidia-nccl-cu12==2.18.1
 nvidia-nvjitlink-cu12==12.3.101
 nvidia-nvtx-cu12==12.1.105
 omegaconf==2.3.0
-onnx==1.17.0
+onnx==1.15.0
 onnxruntime==1.15.1
 openai==1.12.0
 opencv-python==4.8.1.78
-orjson==3.9.15
+orjson==3.9.14
 packaging==23.2
 pandas==2.1.4
 parso==0.8.3
@@ -113,12 +115,11 @@ pdfminer.six==20221105
 pdfplumber==0.10.3
 pexpect==4.9.0
 pikepdf==8.10.1
-Pillow==10.3.0
-pip==23.3.1
+Pillow==10.1.0
 platformdirs==4.1.0
 portalocker==2.8.2
 prompt-toolkit==3.0.43
-protobuf==4.25.1
+protobuf==3.20.3
 psutil==5.9.7
 ptyprocess==0.7.0
 pure-eval==0.2.2
@@ -139,7 +140,7 @@ python-dateutil==2.8.2
 python-dotenv==1.0.1
 python-iso639==2023.12.11
 python-magic==0.4.27
-python-multipart==0.0.18
+python-multipart==0.0.6
 pytz==2023.3.post1
 PyYAML==6.0.1
 pyzmq==25.1.2
@@ -150,50 +151,48 @@ ray==2.9.2
 rdflib==7.0.0
 referencing==0.33.0
 regex==2023.10.3
-requests==2.32.0
+requests==2.31.0
 rpds-py==0.18.0
-safetensors==0.4.1
-scikit-learn==1.5.0
+safetensors==0.5.2
+scikit-learn==1.3.2
 scipy==1.11.4
-sentence-transformers==2.2.2
+sentence-transformers==3.4.1
 sentencepiece==0.1.99
-setuptools==70.0.0
 six==1.16.0
 sniffio==1.3.0
 soupsieve==2.5
 SQLAlchemy==2.0.23
 stack-data==0.6.3
-starlette==0.40.0
+starlette==0.36.3
 sympy==1.12
 tabulate==0.9.0
 tenacity==8.2.3
 threadpoolctl==3.2.0
 tiktoken==0.5.2
 timm==0.9.12
-tokenizers==0.15.0
+tokenizers==0.21.0
 tonic-validate==3.1.0
-torch==2.2.0
+torch==2.1.2
 torchvision==0.16.2
-tornado==6.4.2
-tqdm==4.66.3
+tornado==6.4
+tqdm==4.66.1
 traitlets==5.14.1
-transformers==4.38.0
+transformers==4.48.2
 triton==2.1.0
-typing_extensions==4.9.0
 typing-inspect==0.9.0
+typing_extensions==4.9.0
 tzdata==2023.3
-unstructured==0.14.3
+unstructured==0.11.6
 unstructured-client==0.15.0
 unstructured-inference==0.7.18
 unstructured.pytesseract==0.3.12
-urllib3==2.2.2
+urllib3==2.1.0
 uvicorn==0.27.1
 uvloop==0.19.0
-vllm==0.5.5
+vllm==0.3.1
 watchfiles==0.21.0
 wcwidth==0.2.13
 websockets==12.0
-wheel==0.41.2
 wrapt==1.16.0
 xformers==0.0.23.post1
 xxhash==3.4.1