Upload folder using huggingface_hub

.gitattributes

@@ -32,3 +32,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/GoGalaGames_merged_file.pdf filter=lfs diff=lfs merge=lfs -text
+data/exceloutput.pdf filter=lfs diff=lfs merge=lfs -text
+data/gala_merged_file.pdf filter=lfs diff=lfs merge=lfs -text
+data/googleoutput.pdf filter=lfs diff=lfs merge=lfs -text
+data/merged_file(1).pdf filter=lfs diff=lfs merge=lfs -text
+data/merged_file.pdf filter=lfs diff=lfs merge=lfs -text
+storage/docstore.json filter=lfs diff=lfs merge=lfs -text
+storage/vector_store.json filter=lfs diff=lfs merge=lfs -text

DevSecOpsKB.py

@@ -0,0 +1,51 @@
+from llama_index import SimpleDirectoryReader, LLMPredictor, PromptHelper, StorageContext, ServiceContext, GPTVectorStoreIndex, load_index_from_storage
+from langchain.chat_models import ChatOpenAI
+import gradio as gr
+import sys
+import os
+os.environ["OPENAI_API_KEY"] = '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'
+
+def create_service_context():
+    #constraint parameters
+    max_input_size = 4096
+    num_outputs = 512
+    max_chunk_overlap = 1
+    chunk_size_limit = 600
+    #allows the user to explicitly set certain constraint parameters
+    prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)
+    #LLMPredictor is a wrapper class around LangChain's LLMChain that allows easy integration into LlamaIndex
+    llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.5, model_name="gpt-3.5-turbo", max_tokens=num_outputs))
+    #constructs service_context
+    service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper)
+    return service_context
+
+def data_ingestion_indexing(directory_path):
+    #loads data from the specified directory path
+    documents = SimpleDirectoryReader(directory_path).load_data()
+    
+    #when first building the index
+    index = GPTVectorStoreIndex.from_documents(
+        documents, service_context=create_service_context()
+    )
+    #persist index to disk, default "storage" folder
+    index.storage_context.persist()
+    return index
+
+def data_querying(input_text):
+    #rebuild storage context
+    storage_context = StorageContext.from_defaults(persist_dir="./storage")
+    #loads index from storage
+    index = load_index_from_storage(storage_context, service_context=create_service_context())
+    
+    #queries the index with the input text
+    response = index.as_query_engine().query(input_text)
+    
+    return response.response
+
+iface = gr.Interface(fn=data_querying,
+                     inputs=gr.components.Textbox(lines=7, label="Enter your question"),
+                     outputs="text",
+                     title="Wenqi's Custom-trained DevSecOps Knowledge Base")
+#passes in data directory
+index = data_ingestion_indexing("data")
+iface.launch(share=True)

README.md

@@ -1,12 +1,6 @@
 ---
 title: DevSecOpsKB
-emoji: 👁
-colorFrom: gray
-colorTo: green
+app_file: DevSecOpsKB.py
 sdk: gradio
 sdk_version: 3.33.1
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

data/GoGalaGames_merged_file.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ceba5e5737d9c99eafdd3b4092421768ee37d7013c04043362597ff4f4cec65
+size 5869862

data/exceloutput.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7caa9f587b65b812760e6fa8b76c160c3ae50b84487208f88b1d592e6e50b91f
+size 1949030

data/gala_merged_file.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383c11bd7e7aac553770714e09c9170fd31a664918105c4ef3176dd17bb61fab
+size 77667094

data/googleoutput.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a13caa5c8af957f3a7add03eb68346a8e0920d6336456e98ab818e85322c9a
+size 73853471

data/merged_file(1).pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9c2f58d0fbe8e5931c8cec48cfe7c45ae022ae4aa6a3a298dbcfd62d6563d4
+size 17930742

data/merged_file.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6796e88b9c962a8b266bf2aff0755c70cbb1fe1dce3876d1f0ba8ca383245767
+size 2397296

devsecopskb.log

@@ -0,0 +1,6 @@
+None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
+Token indices sequence length is longer than the specified maximum sequence length for this model (1027 > 1024). Running this sequence through the model will result in indexing errors
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)

storage/docstore.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1684f2606c82d14d22b0b3e0c9767f0e34e24cb58bd79e7230f8624158fcd8
+size 12521629

storage/vector_store.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b3b8614309c5499aef7a6fdeef134590270e0e73d65c0f3a8be2be9483c3b3
+size 154239360