Integration med LLM-frameworks

from langchain_community.vectorstores import Chroma
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_core.documents import Document

# Dummy Embedding Model for demonstration
class DummyEmbeddings(OpenAIEmbeddings):
    def embed_documents(self, texts):
        return [[0.1] * 1536 for _ in texts]
    def embed_query(self, text):
        return [0.1] * 1536

embeddings = DummyEmbeddings()

docs = [
    Document(page_content="The quick brown fox."),
    Document(page_content="AI is transforming industries."),
    Document(page_content="Vector databases are key."),
]

# Create an in-memory Chroma vector store
db = Chroma.from_documents(docs, embeddings)

print("Chroma vector store initialized.")
print(f"Number of documents: {len(docs)}")

from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import CharacterTextSplitter
import os

# Create a dummy text file
with open("sample.txt", "w") as f:
    f.write("This is a long text about RAG. "
            "It combines retrieval with generation. "
            "Vector databases are essential here.")

# Load documents
loader = TextLoader("sample.txt")
documents = loader.load()

# Split documents into chunks
text_splitter = CharacterTextSplitter(
    chunk_size=50, chunk_overlap=0
)
split_docs = text_splitter.split_documents(documents)

print(f"Original doc content: {documents[0].page_content[:40]}...")
print(f"Number of split chunks: {len(split_docs)}")
print(f"First chunk: {split_docs[0].page_content}")

os.remove("sample.txt") # Clean up

from langchain_community.vectorstores import Chroma
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_core.documents import Document

# Dummy Embeddings & Documents
class DummyEmbeddings(OpenAIEmbeddings):
    def embed_documents(self, texts): return [[0.1] * 1536 for _ in texts]
    def embed_query(self, text): return [0.1] * 1536
embeddings = DummyEmbeddings()
docs = [
    Document(page_content="Apples are red."),
    Document(page_content="Bananas are yellow."),
    Document(page_content="Grapes are purple."),
]
db = Chroma.from_documents(docs, embeddings)

# Convert the vector store into a retriever
retriever = db.as_retriever()

query = "What color are grapes?"
retrieved_docs = retriever.invoke(query)

print(f"Query: '{query}'")
print(f"Retrieved {len(retrieved_docs)} documents.")
for i, doc in enumerate(retrieved_docs):
    print(f"  Doc {i+1}: {doc.page_content}")

from llama_index.core import VectorStoreIndex, Document
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.vector_stores.chroma import ChromaVectorStore
import chromadb
from llama_index.core import Settings

# Initialize an in-memory Chroma client
db = chromadb.Client()
chroma_collection = db.get_or_create_collection("my_ll_docs")
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)

# Dummy documents
documents = [
    Document(text="LlamaIndex builds LLM apps."),
    Document(text="It helps with data indexing."),
    Document(text="Vector dbs are core for retrieval."),
]

# Dummy embedding model for runnable example
class DummyLlamaIndexEmbeddings(OpenAIEmbedding):
    def _get_query_embedding(self, query): return [0.2] * 1536
    def _get_text_embedding(self, text): return [0.2] * 1536

Settings.embed_model = DummyLlamaIndexEmbeddings()

# Create a VectorStoreIndex
index = VectorStoreIndex.from_documents(
    documents, vector_store=vector_store
)

print("LlamaIndex VectorStoreIndex created.")

from llama_index.core import VectorStoreIndex, Document
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.vector_stores.chroma import ChromaVectorStore
import chromadb
from llama_index.core import Settings

# Initialize in-memory Chroma client & store
db = chromadb.Client()
chroma_collection = db.get_or_create_collection("my_ll_docs_query")
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)

# Dummy documents
documents = [
    Document(text="LlamaIndex helps build context-augmented LLM apps."),
    Document(text="It provides tools for data ingestion."),
    Document(text="Retrieval is key for RAG."),
]

# Dummy embedding model
class DummyLlamaIndexEmbeddings(OpenAIEmbedding):
    def _get_query_embedding(self, query): return [0.2] * 1536
    def _get_text_embedding(self, text): return [0.2] * 1536

Settings.embed_model = DummyLlamaIndexEmbeddings()

# Create and populate index
index = VectorStoreIndex.from_documents(
    documents, vector_store=vector_store
)

# Create a query engine
query_engine = index.as_query_engine()

# Perform a query
query = "What does LlamaIndex do?"
response = query_engine.query(query)

print(f"Query: '{query}'")
print(f"Response (partial): {str(response)[:80]}...")