Initial commit

.gitignore

+__pycache__
+qdrant_data
+storage
+.DS_Store
+data

1_smoketest.py

+# Just runs .complete to make sure the LLM is listening
+from llama_index.llms import Ollama
+
+llm = Ollama(model="mixtral")
+
+response = llm.complete("Who is Laurie Voss?")
+print(response)

2_index_data.py

+from pathlib import Path
+
+import qdrant_client
+from llama_index import (
+    VectorStoreIndex,
+    ServiceContext,
+    download_loader,
+)
+from llama_index.llms import Ollama
+from llama_index.storage.storage_context import StorageContext
+from llama_index.vector_stores.qdrant import QdrantVectorStore
+
+# load the JSON off disk
+JSONReader = download_loader("JSONReader")
+loader = JSONReader()
+documents = loader.load_data(Path('./data/tinytweets.json'))
+
+# initialize the vector store
+client = qdrant_client.QdrantClient(
+    path="./qdrant_data"
+)
+vector_store = QdrantVectorStore(client=client, collection_name="tweets")
+storage_context = StorageContext.from_defaults(vector_store=vector_store)
+
+# initialize the LLM
+llm = Ollama(model="mixtral")
+service_context = ServiceContext.from_defaults(llm=llm,embed_model="local")
+
+# create the index; this will embed the documents and store them in the vector store
+index = VectorStoreIndex.from_documents(documents,service_context=service_context,storage_context=storage_context)
+
+# query the index
+query_engine = index.as_query_engine()
+response = query_engine.query("What does the author think about Star Trek? Give details.")
+print(response)

3_verify_index.py

+import qdrant_client
+from llama_index import (
+    VectorStoreIndex,
+    ServiceContext,
+)
+from llama_index.llms import Ollama
+from llama_index.vector_stores.qdrant import QdrantVectorStore
+
+import llama_index
+llama_index.set_global_handler("simple")
+
+# re-initialize the vector store
+client = qdrant_client.QdrantClient(
+    path="./qdrant_data"
+)
+vector_store = QdrantVectorStore(client=client, collection_name="tweets")
+
+# get the LLM again
+llm = Ollama(model="mixtral")
+service_context = ServiceContext.from_defaults(llm=llm,embed_model="local")
+
+# load the index from the vector store
+index = VectorStoreIndex.from_vector_store(vector_store=vector_store,service_context=service_context)
+query_engine = index.as_query_engine(similarity_top_k=20)
+response = query_engine.query("Does the author like web frameworks? Give details.")
+print(response)

app.py

+from flask import Flask, request, jsonify
+from flask_cors import CORS, cross_origin
+import qdrant_client
+from llama_index.llms import Ollama
+from llama_index import (
+    VectorStoreIndex,
+    ServiceContext,
+)
+from llama_index.vector_stores.qdrant import QdrantVectorStore
+
+# re-initialize the vector store
+client = qdrant_client.QdrantClient(
+    path="./qdrant_data"
+)
+vector_store = QdrantVectorStore(client=client, collection_name="tweets")
+
+# get the LLM again
+llm = Ollama(model="mixtral")
+service_context = ServiceContext.from_defaults(llm=llm,embed_model="local")
+
+# load the index from the vector store
+index = VectorStoreIndex.from_vector_store(vector_store=vector_store,service_context=service_context)
+
+app = Flask(__name__)
+cors = CORS(app)
+app.config['CORS_HEADERS'] = 'Content-Type'
+
+# This is just so you can easily tell the app is running
+@app.route('/')
+def hello_world():
+    return 'Hello, World!'
+
+@app.route('/process_form', methods=['POST'])
+@cross_origin()
+def process_form():
+    query = request.form.get('query')
+    if query is not None:
+        # query your data!
+        # here we have customized the number of documents returned per query to 20, because tweets are really short
+        query_engine = index.as_query_engine(similarity_top_k=20)
+        response = query_engine.query(query)
+        return jsonify({"response": str(response)})
+    else:
+        return jsonify({"error": "query field is missing"}), 400
+
+if __name__ == '__main__':
+    app.run()

pyproject.toml

+[tool.poetry]
+name = "localmodels"
+version = "0.1.0"
+description = ""
+authors = ["Laurie Voss <github@seldo.com>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.11,<3.13"
+llama-index = "^0.9.19"
+qdrant-client = "^1.7.0"
+transformers = "^4.36.2"
+torch = "^2.1.2"
+flask = "^3.0.0"
+flask-cors = "^4.0.0"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"