Spaces:
Running
Running
File size: 9,437 Bytes
055a3a7 3aa91e9 2f0030b 3aa91e9 b50fffd 3aa91e9 20c7bad 3aa91e9 20c7bad 3aa91e9 055a3a7 3aa91e9 20c7bad 3aa91e9 2f0030b 055a3a7 3aa91e9 055a3a7 20c7bad 3aa91e9 055a3a7 3aa91e9 055a3a7 3aa91e9 055a3a7 3aa91e9 055a3a7 3aa91e9 055a3a7 3aa91e9 055a3a7 3aa91e9 055a3a7 3aa91e9 3f90da8 3aa91e9 2f0030b 3aa91e9 2f0030b 3aa91e9 055a3a7 3aa91e9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 |
"""LlamaIndex RAG service for evidence retrieval and indexing.
Requires optional dependencies: uv sync --extra modal
"""
from typing import Any
import structlog
from src.utils.config import settings
from src.utils.exceptions import ConfigurationError
from src.utils.models import Evidence
logger = structlog.get_logger()
class LlamaIndexRAGService:
"""RAG service using LlamaIndex with ChromaDB vector store.
Note:
This service is currently OpenAI-only. It uses OpenAI embeddings and LLM
regardless of the global `settings.llm_provider` configuration.
Requires OPENAI_API_KEY to be set.
"""
def __init__(
self,
collection_name: str = "deepcritical_evidence",
persist_dir: str | None = None,
embedding_model: str | None = None,
similarity_top_k: int = 5,
) -> None:
"""
Initialize LlamaIndex RAG service.
Args:
collection_name: Name of the ChromaDB collection
persist_dir: Directory to persist ChromaDB data
embedding_model: OpenAI embedding model (defaults to settings.openai_embedding_model)
similarity_top_k: Number of top results to retrieve
"""
# Lazy import - only when instantiated
try:
import chromadb
from llama_index.core import Document, Settings, StorageContext, VectorStoreIndex
from llama_index.core.retrievers import VectorIndexRetriever
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI
from llama_index.vector_stores.chroma import ChromaVectorStore
except ImportError as e:
raise ImportError(
"LlamaIndex dependencies not installed. Run: uv sync --extra modal"
) from e
# Store references for use in other methods
self._chromadb = chromadb
self._Document = Document
self._Settings = Settings
self._StorageContext = StorageContext
self._VectorStoreIndex = VectorStoreIndex
self._VectorIndexRetriever = VectorIndexRetriever
self._ChromaVectorStore = ChromaVectorStore
self.collection_name = collection_name
self.persist_dir = persist_dir or settings.chroma_db_path
self.similarity_top_k = similarity_top_k
self.embedding_model = embedding_model or settings.openai_embedding_model
# Validate API key before use
if not settings.openai_api_key:
raise ConfigurationError("OPENAI_API_KEY required for LlamaIndex RAG service")
# Configure LlamaIndex settings (use centralized config)
self._Settings.llm = OpenAI(
model=settings.openai_model,
api_key=settings.openai_api_key,
)
self._Settings.embed_model = OpenAIEmbedding(
model=self.embedding_model,
api_key=settings.openai_api_key,
)
# Initialize ChromaDB client
self.chroma_client = self._chromadb.PersistentClient(path=self.persist_dir)
# Get or create collection
try:
self.collection = self.chroma_client.get_collection(self.collection_name)
logger.info("loaded_existing_collection", name=self.collection_name)
except Exception:
self.collection = self.chroma_client.create_collection(self.collection_name)
logger.info("created_new_collection", name=self.collection_name)
# Initialize vector store and index
self.vector_store = self._ChromaVectorStore(chroma_collection=self.collection)
self.storage_context = self._StorageContext.from_defaults(vector_store=self.vector_store)
# Try to load existing index, or create empty one
try:
self.index = self._VectorStoreIndex.from_vector_store(
vector_store=self.vector_store,
storage_context=self.storage_context,
)
logger.info("loaded_existing_index")
except Exception:
self.index = self._VectorStoreIndex([], storage_context=self.storage_context)
logger.info("created_new_index")
def ingest_evidence(self, evidence_list: list[Evidence]) -> None:
"""
Ingest evidence into the vector store.
Args:
evidence_list: List of Evidence objects to ingest
"""
if not evidence_list:
logger.warning("no_evidence_to_ingest")
return
# Convert Evidence objects to LlamaIndex Documents
documents = []
for evidence in evidence_list:
metadata = {
"source": evidence.citation.source,
"title": evidence.citation.title,
"url": evidence.citation.url,
"date": evidence.citation.date,
"authors": ", ".join(evidence.citation.authors),
}
doc = self._Document(
text=evidence.content,
metadata=metadata,
doc_id=evidence.citation.url, # Use URL as unique ID
)
documents.append(doc)
# Insert documents into index
try:
for doc in documents:
self.index.insert(doc)
logger.info("ingested_evidence", count=len(documents))
except Exception as e:
logger.error("failed_to_ingest_evidence", error=str(e))
raise
def ingest_documents(self, documents: list[Any]) -> None:
"""
Ingest raw LlamaIndex Documents.
Args:
documents: List of LlamaIndex Document objects
"""
if not documents:
logger.warning("no_documents_to_ingest")
return
try:
for doc in documents:
self.index.insert(doc)
logger.info("ingested_documents", count=len(documents))
except Exception as e:
logger.error("failed_to_ingest_documents", error=str(e))
raise
def retrieve(self, query: str, top_k: int | None = None) -> list[dict[str, Any]]:
"""
Retrieve relevant documents for a query.
Args:
query: Query string
top_k: Number of results to return (defaults to similarity_top_k)
Returns:
List of retrieved documents with metadata and scores
"""
k = top_k or self.similarity_top_k
# Create retriever
retriever = self._VectorIndexRetriever(
index=self.index,
similarity_top_k=k,
)
try:
# Retrieve nodes
nodes = retriever.retrieve(query)
# Convert to dict format
results = []
for node in nodes:
results.append(
{
"text": node.node.get_content(),
"score": node.score,
"metadata": node.node.metadata,
}
)
logger.info("retrieved_documents", query=query[:50], count=len(results))
return results
except Exception as e:
logger.error("failed_to_retrieve", error=str(e), query=query[:50])
raise # Re-raise to allow callers to distinguish errors from empty results
def query(self, query_str: str, top_k: int | None = None) -> str:
"""
Query the RAG system and get a synthesized response.
Args:
query_str: Query string
top_k: Number of results to use (defaults to similarity_top_k)
Returns:
Synthesized response string
"""
k = top_k or self.similarity_top_k
# Create query engine
query_engine = self.index.as_query_engine(
similarity_top_k=k,
)
try:
response = query_engine.query(query_str)
logger.info("generated_response", query=query_str[:50])
return str(response)
except Exception as e:
logger.error("failed_to_query", error=str(e), query=query_str[:50])
raise # Re-raise to allow callers to handle errors explicitly
def clear_collection(self) -> None:
"""Clear all documents from the collection."""
try:
self.chroma_client.delete_collection(self.collection_name)
self.collection = self.chroma_client.create_collection(self.collection_name)
self.vector_store = self._ChromaVectorStore(chroma_collection=self.collection)
self.storage_context = self._StorageContext.from_defaults(
vector_store=self.vector_store
)
self.index = self._VectorStoreIndex([], storage_context=self.storage_context)
logger.info("cleared_collection", name=self.collection_name)
except Exception as e:
logger.error("failed_to_clear_collection", error=str(e))
raise
def get_rag_service(
collection_name: str = "deepcritical_evidence",
**kwargs: Any,
) -> LlamaIndexRAGService:
"""
Get or create a RAG service instance.
Args:
collection_name: Name of the ChromaDB collection
**kwargs: Additional arguments for LlamaIndexRAGService
Returns:
Configured LlamaIndexRAGService instance
"""
return LlamaIndexRAGService(collection_name=collection_name, **kwargs)
|