Skip to content

A curated collection of practical AI projects implementing OCR systems, RAG, AI agents, and other AI use cases.

fix(graphrag_knowledge_system): remove unresolved merge conflict markers

Rudy Celeklib730ab79595d
diff --git a/rag_apps/graphrag_knowledge_system/.env.example b/rag_apps/graphrag_knowledge_system/.env.example
index 570cab1..54aa524 100644
--- a/rag_apps/graphrag_knowledge_system/.env.example
+++ b/rag_apps/graphrag_knowledge_system/.env.example
@@ -1,12 +1,6 @@
-<<<<<<< HEAD
-MISTRAL_API_KEY=your_mistral_api_key_here
-
-# Optional — defaults to http://localhost:11434
-=======
# Mistral API key used for entity extraction and answer generation.
# Get one free at https://platform.mistral.ai
MISTRAL_API_KEY=your_mistral_api_key_here
# Optional, defaults to http://localhost:11434
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
# OLLAMA_BASE_URL=http://localhost:11434
diff --git a/rag_apps/graphrag_knowledge_system/app.py b/rag_apps/graphrag_knowledge_system/app.py
index 3161982..12c8aba 100644
--- a/rag_apps/graphrag_knowledge_system/app.py
+++ b/rag_apps/graphrag_knowledge_system/app.py
@@ -1,11 +1,8 @@
-<<<<<<< HEAD
-=======
"""
GraphRAG Knowledge System Streamlit app: document ingestion, knowledge graph
construction, community detection, and Local/Global search over the graph.
"""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
import uuid
import json
import os
@@ -77,10 +74,7 @@ st.markdown(
@st.cache_resource(show_spinner=False)
def get_components():
-<<<<<<< HEAD
-=======
"""Construct and cache the pipeline components shared across reruns."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
graph_store = GraphStore()
vector_store = VectorStore()
entity_extractor = EntityExtractor()
@@ -117,10 +111,7 @@ Summary:"""
def run_community_detection(
graph_store: GraphStore, llm_client: LLMClient, status_fn
) -> int:
-<<<<<<< HEAD
-=======
"""Detect entity communities in the graph and summarise each one with the LLM."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
full_graph = graph_store.get_full_graph()
entities = full_graph["entities"]
relationships = full_graph["relationships"]
@@ -195,20 +186,13 @@ def ingest_document(
cache_manager: CacheManager,
llm_client: LLMClient,
) -> dict:
-<<<<<<< HEAD
-=======
"""Chunk, extract entities from, and index a single uploaded document."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
file_hash = cache_manager.file_hash(file_content)
if cache_manager.is_processed(file_hash):
return {
"status": "cached",
-<<<<<<< HEAD
- "message": f"'{filename}' was already processed — skipping.",
-=======
"message": f"'{filename}' was already processed, skipping.",
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
}
# ── Step 1: Load and chunk ────────────────────────────────────────────────
@@ -238,11 +222,7 @@ def ingest_document(
chunk_id = f"{doc_id}_chunk_{idx}"
chunk_text = chunk.page_content
-<<<<<<< HEAD
- # Store chunk in Neo4j
-=======
# Store chunk in the knowledge graph
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
graph_store.create_chunk(chunk_id, chunk_text, doc_id)
# Extract entities and relationships
@@ -324,10 +304,7 @@ TYPE_COLORS = {
def _type_badge(entity_type: str) -> str:
-<<<<<<< HEAD
-=======
"""Render an entity type as a small colored HTML badge."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
color = TYPE_COLORS.get(entity_type, "#888")
return (
f'<span style="background:{color};color:#fff;padding:2px 10px;'
@@ -337,10 +314,7 @@ def _type_badge(entity_type: str) -> str:
def render_entity_list(entities: list):
-<<<<<<< HEAD
-=======
"""Render up to 20 entities as name, description, and type badge rows."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if not entities:
st.caption("No entities retrieved.")
return
@@ -359,10 +333,7 @@ def render_entity_list(entities: list):
def render_relationship_list(relationships: list):
-<<<<<<< HEAD
-=======
"""Render up to 15 relationships as source-target-weight rows."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if not relationships:
st.caption("No relationships retrieved.")
return
@@ -381,10 +352,7 @@ def render_relationship_list(relationships: list):
def main():
-<<<<<<< HEAD
-=======
"""Render the Streamlit page: ingestion sidebar, search controls, and results."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
# ── Header ────────────────────────────────────────────────────────────────
st.markdown(
'<div class="main-header">🕸️ GraphRAG Knowledge System</div>', unsafe_allow_html=True
@@ -408,13 +376,8 @@ def main():
except Exception as e:
st.error(f"Failed to initialise components: {e}")
st.info(
-<<<<<<< HEAD
- "Check your `.env` file — make sure NEO4J_URI, NEO4J_PASSWORD, "
- "MISTRAL_API_KEY are set and Ollama is running on http://localhost:11434"
-=======
"Check your `.env` file, make sure MISTRAL_API_KEY is set "
"and Ollama is running on http://localhost:11434"
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
)
get_components.clear()
return
@@ -440,11 +403,7 @@ def main():
"Upload PDF or TXT files",
type=["pdf", "txt"],
accept_multiple_files=True,
-<<<<<<< HEAD
- help="Documents are chunked, entity-extracted, and stored in Neo4j + ChromaDB.",
-=======
help="Documents are chunked, entity-extracted, and stored in the local knowledge graph and ChromaDB.",
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
)
if uploaded_files and st.button("⚙️ Process Documents", type="primary", use_container_width=True):
@@ -486,21 +445,13 @@ def main():
try:
st.metric("Chunks", vector_store.count())
except Exception:
-<<<<<<< HEAD
- st.metric("Chunks", "—")
-=======
st.metric("Chunks", "N/A")
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
with col2:
try:
communities = graph_store.get_all_communities()
st.metric("Communities", len(communities))
except Exception:
-<<<<<<< HEAD
- st.metric("Communities", "—")
-=======
st.metric("Communities", "N/A")
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if st.button("🔄 Refresh Stats", use_container_width=True):
st.rerun()
@@ -546,11 +497,7 @@ def main():
# ── Answer ────────────────────────────────────────────────────────────
mode_label = "Local Search" if "Local" in search_mode else "Global Search"
-<<<<<<< HEAD
- st.markdown(f"### Answer — {mode_label}")
-=======
st.markdown(f"### Answer: {mode_label}")
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
st.markdown(result["answer"])
# ── Supporting context ────────────────────────────────────────────────
@@ -597,11 +544,7 @@ def main():
with info_col2:
st.info(
"**2. Knowledge Graph Built**\n\n"
-<<<<<<< HEAD
- "Entities and relationships are stored in Neo4j. "
-=======
"Entities and relationships are stored in the local knowledge graph. "
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
"Text embeddings go into ChromaDB via Ollama."
)
with info_col3:
diff --git a/rag_apps/graphrag_knowledge_system/src/cache_manager.py b/rag_apps/graphrag_knowledge_system/src/cache_manager.py
index f775fce..289b4c0 100644
--- a/rag_apps/graphrag_knowledge_system/src/cache_manager.py
+++ b/rag_apps/graphrag_knowledge_system/src/cache_manager.py
@@ -6,18 +6,12 @@ from pathlib import Path
class CacheManager:
def __init__(self, cache_path: str = "./cache.json"):
-<<<<<<< HEAD
-=======
"""Load the processed-file cache from disk."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
self.cache_path = Path(cache_path)
self._load()
def _load(self):
-<<<<<<< HEAD
-=======
"""Read the cache JSON file from disk, or start empty if none exists."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if self.cache_path.exists():
with open(self.cache_path, "r") as f:
self.cache = json.load(f)
@@ -25,34 +19,22 @@ class CacheManager:
self.cache = {}
def _save(self):
-<<<<<<< HEAD
-=======
"""Write the current cache to disk as JSON."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
with open(self.cache_path, "w") as f:
json.dump(self.cache, f, indent=2)
def file_hash(self, content: bytes) -> str:
-<<<<<<< HEAD
- return hashlib.sha256(content).hexdigest()
-
- def is_processed(self, file_hash: str) -> bool:
-=======
"""Compute a SHA-256 hash of the given file content."""
return hashlib.sha256(content).hexdigest()
def is_processed(self, file_hash: str) -> bool:
"""Check whether a file with this hash has already been indexed."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
return file_hash in self.cache
def mark_processed(
self, file_hash: str, filename: str, doc_id: str, chunk_count: int
):
-<<<<<<< HEAD
-=======
"""Record a file as processed and persist the cache."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
self.cache[file_hash] = {
"filename": filename,
"document_id": doc_id,
@@ -62,10 +44,7 @@ class CacheManager:
self._save()
def get_all(self) -> list:
-<<<<<<< HEAD
-=======
"""Return summary info for every processed file in the cache."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
return [
{
"filename": v["filename"],
@@ -77,10 +56,7 @@ class CacheManager:
]
def remove(self, file_hash: str):
-<<<<<<< HEAD
-=======
"""Remove a file's cache entry, if present, and persist the change."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if file_hash in self.cache:
del self.cache[file_hash]
self._save()
diff --git a/rag_apps/graphrag_knowledge_system/src/document_processor.py b/rag_apps/graphrag_knowledge_system/src/document_processor.py
index c40e429..c34b169 100644
--- a/rag_apps/graphrag_knowledge_system/src/document_processor.py
+++ b/rag_apps/graphrag_knowledge_system/src/document_processor.py
@@ -8,10 +8,7 @@ from langchain_community.document_loaders import PyPDFLoader, TextLoader
class DocumentProcessor:
def __init__(self, chunk_size: int = 800, chunk_overlap: int = 150):
-<<<<<<< HEAD
-=======
"""Configure the text splitter used to chunk loaded documents."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
self.splitter = RecursiveCharacterTextSplitter(
chunk_size=chunk_size,
chunk_overlap=chunk_overlap,
@@ -19,10 +16,7 @@ class DocumentProcessor:
)
def process(self, file_content: bytes, filename: str) -> list:
-<<<<<<< HEAD
-=======
"""Load a PDF or TXT file from bytes and split it into text chunks."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
suffix = Path(filename).suffix.lower()
if suffix not in {".pdf", ".txt"}:
raise ValueError(f"Unsupported file type: {suffix}. Use PDF or TXT.")
diff --git a/rag_apps/graphrag_knowledge_system/src/entity_extractor.py b/rag_apps/graphrag_knowledge_system/src/entity_extractor.py
index 0cdebbd..615876c 100644
--- a/rag_apps/graphrag_knowledge_system/src/entity_extractor.py
+++ b/rag_apps/graphrag_knowledge_system/src/entity_extractor.py
@@ -28,11 +28,7 @@ Extraction rules:
- Extract 3–12 meaningful, specific entities; skip generic words
- Every relationship source and target MUST be an entity you extracted
- weight is 0.0–1.0 reflecting relationship strength or importance
-<<<<<<< HEAD
-- Return only valid JSON — no markdown fences, no extra text
-=======
- Return only valid JSON, no markdown fences, no extra text
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
Text to analyze:
{text}"""
@@ -40,17 +36,11 @@ Text to analyze:
class EntityExtractor:
def __init__(self):
-<<<<<<< HEAD
- self.llm = LLMClient()
-
- def extract(self, text: str, chunk_id: str) -> dict:
-=======
"""Create the LLM client used for entity and relationship extraction."""
self.llm = LLMClient()
def extract(self, text: str, chunk_id: str) -> dict:
"""Extract typed entities and weighted relationships from a text chunk via Mistral."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
prompt = EXTRACTION_PROMPT.format(text=text[:3000])
try:
diff --git a/rag_apps/graphrag_knowledge_system/src/graph_store.py b/rag_apps/graphrag_knowledge_system/src/graph_store.py
index e1210c8..3012fc7 100644
--- a/rag_apps/graphrag_knowledge_system/src/graph_store.py
+++ b/rag_apps/graphrag_knowledge_system/src/graph_store.py
@@ -12,20 +12,14 @@ class GraphStore:
"""
def __init__(self, persist_path: str = "./graph_store.json"):
-<<<<<<< HEAD
-=======
"""Load the persisted graph from disk, or start a fresh one if none exists."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
self.persist_path = Path(persist_path)
self.G: nx.DiGraph = self._load()
# ── Persistence ───────────────────────────────────────────────────────────
def _load(self) -> nx.DiGraph:
-<<<<<<< HEAD
-=======
"""Read the graph JSON file from disk and rebuild it as a DiGraph."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if self.persist_path.exists():
try:
with open(self.persist_path, "r", encoding="utf-8") as f:
@@ -36,10 +30,7 @@ class GraphStore:
return nx.DiGraph()
def _save(self):
-<<<<<<< HEAD
-=======
"""Serialise the current graph to disk as JSON."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
data = nx.node_link_data(self.G)
with open(self.persist_path, "w", encoding="utf-8") as f:
json.dump(data, f, ensure_ascii=False)
@@ -47,20 +38,14 @@ class GraphStore:
# ── Document ─────────────────────────────────────────────────────────────
def create_document(self, doc_id: str, filename: str, file_hash: str):
-<<<<<<< HEAD
-=======
"""Add a document node to the graph and persist the change."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
self.G.add_node(
doc_id, node_type="document", filename=filename, file_hash=file_hash
)
self._save()
def document_exists(self, file_hash: str) -> bool:
-<<<<<<< HEAD
-=======
"""Check whether a document with the given file hash is already in the graph."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
return any(
d.get("node_type") == "document" and d.get("file_hash") == file_hash
for _, d in self.G.nodes(data=True)
@@ -69,10 +54,7 @@ class GraphStore:
# ── Chunks ────────────────────────────────────────────────────────────────
def create_chunk(self, chunk_id: str, content: str, doc_id: str):
-<<<<<<< HEAD
-=======
"""Add a chunk node linked to its parent document and persist the change."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
self.G.add_node(chunk_id, node_type="chunk", content=content, doc_id=doc_id)
if self.G.has_node(doc_id):
self.G.add_edge(chunk_id, doc_id, rel_type="PART_OF")
@@ -83,10 +65,7 @@ class GraphStore:
def upsert_entity(
self, name: str, entity_type: str, description: str, chunk_id: str
):
-<<<<<<< HEAD
-=======
"""Create or update an entity node and link it to the chunk it appeared in."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if self.G.has_node(name) and self.G.nodes[name].get("node_type") == "entity":
existing = self.G.nodes[name]
if len(description) > len(existing.get("description", "")):
@@ -109,10 +88,7 @@ class GraphStore:
def upsert_relationship(
self, source: str, target: str, description: str, weight: float
):
-<<<<<<< HEAD
-=======
"""Create a relationship edge between two entities, or average the weight if it exists."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if not self.G.has_node(source) or not self.G.has_node(target):
return
if self.G.has_edge(source, target):
@@ -134,22 +110,15 @@ class GraphStore:
# ── Community ─────────────────────────────────────────────────────────────
def set_entity_community(self, entity_name: str, community_id: str):
-<<<<<<< HEAD
- # No _save() here — called in a tight loop; caller saves via create_community()
-=======
"""Tag an entity node with the community it belongs to."""
# No _save() here since this runs in a tight loop; caller saves via create_community()
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if self.G.has_node(entity_name):
self.G.nodes[entity_name]["community_id"] = community_id
def create_community(
self, community_id: str, entity_names: List[str], summary: str, level: int = 0
):
-<<<<<<< HEAD
-=======
"""Add a community node, link its member entities, and persist the change."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
self.G.add_node(
community_id,
node_type="community",
@@ -163,10 +132,7 @@ class GraphStore:
self._save()
def get_all_communities(self) -> List[Dict]:
-<<<<<<< HEAD
-=======
"""Return every community node along with its member entity names."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
result = []
for node_id, data in self.G.nodes(data=True):
if data.get("node_type") != "community":
@@ -188,10 +154,7 @@ class GraphStore:
return result
def communities_exist(self) -> bool:
-<<<<<<< HEAD
-=======
"""Check whether any community nodes have been created yet."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
return any(
d.get("node_type") == "community" for _, d in self.G.nodes(data=True)
)
@@ -199,10 +162,7 @@ class GraphStore:
# ── Graph export for community detection ─────────────────────────────────
def get_full_graph(self) -> Dict:
-<<<<<<< HEAD
-=======
"""Return every entity and weighted relationship in the graph for community detection."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
entities = [
{"name": n, "type": d.get("type", "")}
for n, d in self.G.nodes(data=True)
@@ -216,10 +176,7 @@ class GraphStore:
return {"entities": entities, "relationships": relationships}
def get_entity_descriptions(self, names: List[str]) -> List[Dict]:
-<<<<<<< HEAD
-=======
"""Look up name, type, and description for each entity in the given list."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
result = []
for name in names:
if not self.G.has_node(name):
@@ -238,10 +195,7 @@ class GraphStore:
# ── Search context ────────────────────────────────────────────────────────
def get_entity_neighborhood(self, entity_names: List[str]) -> Dict:
-<<<<<<< HEAD
-=======
"""Collect the given entities plus everything directly related to them."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
seen_entities: set = set()
seen_rels: set = set()
entities: List[Dict] = []
@@ -293,15 +247,9 @@ class GraphStore:
# ── Helpers ───────────────────────────────────────────────────────────────
def ping(self) -> Tuple[bool, str]:
-<<<<<<< HEAD
- return True, "Connected (local NetworkX graph)"
-
- def close(self):
-=======
"""Report that the local graph store is always available."""
return True, "Connected (local NetworkX graph)"
def close(self):
"""Persist the graph to disk before shutting down."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
self._save()
diff --git a/rag_apps/graphrag_knowledge_system/src/llm_client.py b/rag_apps/graphrag_knowledge_system/src/llm_client.py
index 452bcc8..3c570ae 100644
--- a/rag_apps/graphrag_knowledge_system/src/llm_client.py
+++ b/rag_apps/graphrag_knowledge_system/src/llm_client.py
@@ -6,10 +6,7 @@ from langchain_core.messages import HumanMessage, SystemMessage
class LLMClient:
def __init__(self):
-<<<<<<< HEAD
-=======
"""Create the plain-text and JSON-mode Mistral chat clients."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
api_key = os.getenv("MISTRAL_API_KEY")
if not api_key:
raise ValueError("MISTRAL_API_KEY not set in environment")
@@ -26,10 +23,7 @@ class LLMClient:
)
def complete(self, prompt: str, json_mode: bool = False, max_retries: int = 3) -> str:
-<<<<<<< HEAD
-=======
"""Send a single prompt to Mistral, retrying with backoff on failure."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
client = self.llm_json if json_mode else self.llm
messages = [HumanMessage(content=prompt)]
for attempt in range(max_retries):
@@ -45,10 +39,7 @@ class LLMClient:
def complete_with_system(
self, system: str, user: str, json_mode: bool = False
) -> str:
-<<<<<<< HEAD
-=======
"""Send a system and user message pair to Mistral and return the response text."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
client = self.llm_json if json_mode else self.llm
messages = [SystemMessage(content=system), HumanMessage(content=user)]
response = client.invoke(messages)
diff --git a/rag_apps/graphrag_knowledge_system/src/search_engine.py b/rag_apps/graphrag_knowledge_system/src/search_engine.py
index bb082db..10cf18d 100644
--- a/rag_apps/graphrag_knowledge_system/src/search_engine.py
+++ b/rag_apps/graphrag_knowledge_system/src/search_engine.py
@@ -59,10 +59,7 @@ Answer:"""
class SearchEngine:
def __init__(self, graph_store: GraphStore, vector_store: VectorStore):
-<<<<<<< HEAD
-=======
"""Wire up the graph store, vector store, and LLM client used for search."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
self.graph = graph_store
self.vector = vector_store
self.llm = LLMClient()
@@ -70,10 +67,7 @@ class SearchEngine:
# ── Local Search ──────────────────────────────────────────────────────────
def local_search(self, query: str, n_chunks: int = 5) -> Dict:
-<<<<<<< HEAD
-=======
"""Retrieve matching chunks and their graph context, then answer the question."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
if self.vector.count() == 0:
return self._no_docs_result()
@@ -132,10 +126,7 @@ class SearchEngine:
# ── Global Search ─────────────────────────────────────────────────────────
def global_search(self, query: str) -> Dict:
-<<<<<<< HEAD
-=======
"""Rate each community's relevance to the question and synthesise an answer from the top ones."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
communities = self.graph.get_all_communities()
if not communities:
return self.local_search(query)
@@ -208,10 +199,7 @@ class SearchEngine:
@staticmethod
def _no_docs_result() -> Dict:
-<<<<<<< HEAD
-=======
"""Build the placeholder result returned when no documents have been indexed."""
->>>>>>> 1d1e9f137cfd1123edbae5d8e955ce0b9c7fcf4a
return {
"answer": "No documents have been indexed yet. Please upload and process documents first.",
"entities": [],