Feature/issue 25 llm for noc code lookup

bedrock-rag-2.py

@@ -0,0 +1,117 @@
+import boto3
+import os.path
+import json
+import csv
+from langchain_community.vectorstores import Chroma
+from langchain_community.llms import Bedrock
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from langchain_community.embeddings import OllamaEmbeddings
+from langchain.docstore.document import Document
+
+def get_bedrock_client():
+    session = boto3.Session()
+    bedrock_client_internal = session.client(
+        service_name='bedrock-runtime',
+        region_name='us-east-1',
+    )
+    return bedrock_client_internal
+
+
+def load_embeddings():
+    return Chroma(
+        collection_name="rag-chroma",
+        embedding_function=OllamaEmbeddings(model='nomic-embed-text'),
+        persist_directory="./chroma_db_bedrock"
+    )
+
+# Filter out duplicate codes
+def include_code(row):
+    return row['code'] not in ['11', '1', '0', '14', '12', '13', '10' ]
+
+def to_page_content(code):
+    return json.dumps(code)
+
+def compute_embeddings():
+    noc_codes = []
+    with open('data/noc.csv', newline='') as csvfile:
+        noc_codes = [
+            { 'code': row['Code - NOC 2021 V1.0'], 'title': row['Class title'], 'definition': row['Class definition'] } 
+            for row in csv.DictReader(csvfile)
+        ]
+    filtered_noc_codes = [code for code in noc_codes if include_code(code)]
+    documents = [Document(
+        page_content=to_page_content(code), 
+        metadata={'code': code['code']}
+    ) for code in filtered_noc_codes]
+    print('total documents included = ', len(documents))
+
+    return Chroma.from_documents(
+        documents=documents,
+        collection_name="rag-chroma",
+        embedding=OllamaEmbeddings(model='nomic-embed-text'),
+        persist_directory="./chroma_db_bedrock"
+    )
+
+def load_or_compute_embeddings():
+    embeddings_exist = os.path.isfile("./chroma_db/chroma.sqlite3")
+    return load_embeddings() if embeddings_exist else compute_embeddings()
+
+
+
+
+#### not used ####
+# def create_vector_db_chroma_index(chroma_db_path: str):
+    # #replace the document path here for pdf ingestion
+    # loader = PyPDFLoader(os.path.join("./", "data", "Doc2.pdf"))
+    # doc = loader.load()
+    # text_splitter = CharacterTextSplitter(chunk_size=2000, separator="\n")
+    # chunks = text_splitter.split_documents(doc)
+    # emb_model = "sentence-transformers/all-MiniLM-L6-v2"
+    # embeddings = HuggingFaceEmbeddings(
+        # model_name=emb_model,
+        # cache_folder="./cache/"
+    # )
+    # db = Chroma.from_documents(chunks,
+                               # embedding=embeddings,
+                               # persist_directory=chroma_db_path)
+    # db.persist()
+    # return db
+
+def doit():
+    bedrock_boto3_client = get_bedrock_client()
+    chroma_db = load_or_compute_embeddings()
+    retriever = chroma_db.as_retriever()
+    llm = Bedrock(
+        model_id="anthropic.claude-instant-v1", 
+        client=bedrock_boto3_client, 
+        model_kwargs={
+            "max_tokens_to_sample": 512, 
+            "temperature": 0
+            }
+        )
+
+    template = """\n\nHuman:Use the following pieces of context to answer the question at the end. 
+    If you don't know the answer, just say that you don't know, don't try to make up an answer. 
+    Use three sentences maximum and keep the answer as concise as possible.
+    {context}
+    Question: {question}
+    \n\nAssistant:"""
+
+    memory = ConversationBufferMemory(
+        memory_key='chat_history', 
+        return_messages=False
+    )
+
+    conv_qa_chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=retriever,
+        memory=memory,
+        return_source_documents=False
+    )
+
+    returnval = conv_qa_chain("is application development covered?")
+    print(returnval["answer"])
+
+if __name__ == '__main__':
+    doit()

bedrock-rag.py

@@ -0,0 +1,107 @@
+import boto3
+import json
+import os
+from dotenv import load_dotenv
+load_dotenv()
+
+boto_client = boto3.client(service_name='bedrock-runtime',
+                   aws_access_key_id=os.getenv('AWS_ACCESS_KEY_ID'),
+                   aws_secret_access_key=os.getenv('AWS_SECRET_ACCESS_KEY'))
+
+body = json.dumps({
+    "prompt": "\n\nHuman: explain white holes to 8th graders\n\nAssistant:",
+    "maxTokens": 300,
+    "temperature": 0.1,
+    # "topP": 0.9,
+})
+
+# https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-jurassic2.html
+modelId = 'ai21.j2-ultra-v1'
+accept = 'application/json'
+contentType = 'application/json'
+
+# print("boto client list models...")
+# print(json.dumps(boto_client.list_models()))
+# print("boto client list models done")
+
+response = boto_client.invoke_model(
+    body=body, 
+    modelId=modelId, 
+    accept=accept, 
+    contentType=contentType
+)
+
+response_body = json.loads(response.get('body').read())
+
+print(response_body['completions'][0].get('data').get('text'))
+
+
+
+# -----------------------
+exit()
+
+def load_embeddings():
+    return Chroma(
+        collection_name="rag-chroma",
+        embedding_function=OllamaEmbeddings(model='nomic-embed-text'),
+        persist_directory="./chroma_db"
+    )
+
+noc_codes = []
+
+with open('data/noc.csv', newline='') as csvfile:
+    noc_codes = [
+        { 'code': row['Code - NOC 2021 V1.0'], 'title': row['Class title'], 'definition': row['Class definition'] } 
+        for row in csv.DictReader(csvfile)
+    ]
+
+# Filter out duplicate codes
+def include_code(row):
+    return row['code'] not in ['11', '1', '0', '14', '12', '13', '10' ]
+
+filtered_noc_codes = [code for code in noc_codes if include_code(code)]
+
+def to_page_content(code):
+    return json.dumps(code)
+
+documents = [Document(
+        page_content=to_page_content(code), 
+        metadata={'code': code['code']}
+    ) for code in filtered_noc_codes]
+
+def compute_embeddings():
+    return Chroma.from_documents(
+        documents=documents,
+        collection_name="rag-chroma",
+        embedding=OllamaEmbeddings(model='nomic-embed-text'),
+        persist_directory="./chroma_db"
+    )
+
+def load_or_compute_embeddings():
+    embeddings_exist = os.path.isfile("./chroma_db/chroma.sqlite3")
+    return load_embeddings() if embeddings_exist else compute_embeddings()
+
+embeddings = load_or_compute_embeddings()
+
+retriever = embeddings.as_retriever()
+
+after_rag_template = """Answer the question based only on the following context:
+{context}
+Question: {question}
+"""
+
+after_rag_prompt = ChatPromptTemplate.from_template(after_rag_template)
+
+model_local = ChatOllama(model="noc_master")
+
+# model_local is the OLLAMA model
+# need to find a way to use the model from the boto client...
+
+after_rag_chain = (
+    {"context": retriever, "question": RunnablePassthrough()}
+    | after_rag_prompt
+    | model_local
+    | StrOutputParser()
+)
+
+print(after_rag_chain.invoke(prompt))

bedrock.requirements

@@ -0,0 +1,103 @@
+aiohttp==3.9.3
+aiosignal==1.3.1
+annotated-types==0.6.0
+anyio==4.3.0
+asgiref==3.8.0
+async-timeout==4.0.3
+attrs==23.2.0
+backoff==2.2.1
+bcrypt==4.1.2
+boto3==1.34.67
+botocore==1.34.67
+build==1.1.1
+cachetools==5.3.3
+certifi==2024.2.2
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.3
+chromadb==0.4.24
+click==8.1.7
+coloredlogs==15.0.1
+dataclasses-json==0.6.4
+Deprecated==1.2.14
+exceptiongroup==1.2.0
+fastapi==0.110.0
+filelock==3.13.1
+flatbuffers==24.3.7
+frozenlist==1.4.1
+fsspec==2024.3.1
+google-auth==2.29.0
+googleapis-common-protos==1.63.0
+grpcio==1.62.1
+h11==0.14.0
+httptools==0.6.1
+huggingface-hub==0.21.4
+humanfriendly==10.0
+idna==3.6
+importlib-metadata==6.11.0
+importlib_resources==6.4.0
+jmespath==1.0.1
+jsonpatch==1.33
+jsonpointer==2.4
+kubernetes==29.0.0
+langchain-community==0.0.29
+langchain-core==0.1.33
+langsmith==0.1.31
+marshmallow==3.21.1
+mmh3==4.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.5
+mypy-extensions==1.0.0
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.17.1
+opentelemetry-api==1.23.0
+opentelemetry-exporter-otlp-proto-common==1.23.0
+opentelemetry-exporter-otlp-proto-grpc==1.23.0
+opentelemetry-instrumentation==0.44b0
+opentelemetry-instrumentation-asgi==0.44b0
+opentelemetry-instrumentation-fastapi==0.44b0
+opentelemetry-proto==1.23.0
+opentelemetry-sdk==1.23.0
+opentelemetry-semantic-conventions==0.44b0
+opentelemetry-util-http==0.44b0
+orjson==3.9.15
+overrides==7.7.0
+packaging==23.2
+posthog==3.5.0
+protobuf==4.25.3
+pulsar-client==3.4.0
+pyasn1==0.5.1
+pyasn1-modules==0.3.0
+pydantic==2.6.4
+pydantic_core==2.16.3
+PyPika==0.48.9
+pyproject_hooks==1.0.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+PyYAML==6.0.1
+requests==2.31.0
+requests-oauthlib==1.4.0
+rsa==4.9
+s3transfer==0.10.1
+six==1.16.0
+sniffio==1.3.1
+SQLAlchemy==2.0.28
+starlette==0.36.3
+sympy==1.12
+tenacity==8.2.3
+tokenizers==0.15.2
+tomli==2.0.1
+tqdm==4.66.2
+typer==0.9.0
+typing-inspect==0.9.0
+typing_extensions==4.10.0
+urllib3==1.26.18
+uvicorn==0.29.0
+uvloop==0.19.0
+watchfiles==0.21.0
+websocket-client==1.7.0
+websockets==12.0
+wrapt==1.16.0
+yarl==1.9.4
+zipp==3.18.1