Merge pull request #223 from neo4j-labs/DEV

Dev To Staging

Author: karanchellani

.gitignore

@@ -162,4 +162,6 @@ cython_debug/
 temp.pdf
 google-cloud-sdk
 google-cloud-cli-469.0.0-linux-x86_64.tar.gz
-/data/llm-experiments-387609-c73d512ca3b1.json
+/data/llm-experiments-387609-c73d512ca3b1.json
+/backend/src/merged_files
+/backend/src/chunks

README.md

@@ -74,7 +74,7 @@ KNN_MIN_SCORE = ""\
    	 userName: Username to use for graph creation ( if None will use username from config file )
    	 password: Password to use for graph creation ( if None will use password from config file )
    	 file: File object containing the PDF file path to be used
-   	 model: Type of model to use ('OpenAI GPT 3.5' or 'OpenAI GPT 4')
+   	 model: Type of model to use ('Gemini Pro' or 'Diffbot')
    
      Returns: 
    	 Json response to API with fileName, nodeCount, relationshipCount, processingTime, 

backend/Dockerfile

@@ -10,17 +10,5 @@ RUN apt-get update \
     && export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH \
     && pip install --no-cache-dir --upgrade -r /code/requirements.txt
 
-# Installing gcloud
-#RUN curl https://dl.google.com/dl/cloudsdk/release/google-cloud-sdk.tar.gz > /tmp/google-cloud-sdk.tar.gz
-
-# Installing the package
-#RUN mkdir -p /usr/local/gcloud \
-#  && tar -C /usr/local/gcloud -xvf /tmp/google-cloud-sdk.tar.gz \
-#  && /usr/local/gcloud/google-cloud-sdk/install.sh
-
-# Adding the package path to local
-#ENV PATH $PATH:/usr/local/gcloud/google-cloud-sdk/bin
-
 CMD ["uvicorn", "score:app", "--host", "0.0.0.0", "--port", "8000"]
-#CMD ["gcloud", "auth", "application-default", "login", "--quiet", "--no-user-output-enabled"]
 

backend/example.env

@@ -12,4 +12,5 @@ KNN_MIN_SCORE = ""
 LANGCHAIN_API_KEY = ""
 LANGCHAIN_PROJECT = ""
 LANGCHAIN_TRACING_V2 = ""
-LANGCHAIN_ENDPOINT = ""
+LANGCHAIN_ENDPOINT = ""
+NUMBER_OF_CHUNKS_TO_COMBINE = ""

backend/requirements.txt

@@ -28,8 +28,8 @@ docstring_parser==0.16
 effdet==0.4.1
 emoji==2.10.1
 exceptiongroup==1.2.0
-fastapi==0.110.0
-fastapi-health==0.4.0
+fastapi
+fastapi-health
 filelock==3.13.1
 filetype==1.2.0
 flatbuffers==23.5.26
@@ -38,7 +38,7 @@ frozenlist==1.4.1
 fsspec==2024.2.0
 google-api-core==2.18.0
 google-auth==2.29.0
-google-cloud-aiplatform==1.46.0
+google-cloud-aiplatform
 google-cloud-bigquery==3.19.0
 google-cloud-core==2.4.1
 google-cloud-resource-manager==1.12.3
@@ -158,9 +158,10 @@ unstructured-client
 unstructured-inference
 unstructured.pytesseract
 urllib3
-uvicorn==0.29.0
+uvicorn
 wikipedia==1.4.0
 wrapt==1.16.0
 yarl==1.9.4
 youtube-transcript-api==0.6.2
 zipp==3.17.0
+sentence-transformers