apunkt/trustgraph
1
0
Fork 0
mirror of https://github.com/trustgraph-ai/trustgraph.git synced 2026-05-20 12:55:13 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Embeddings API scores (#671)

Browse source 
- Put scores in all responses
- Remove unused 'middle' vector layer. Vector of texts -> vector of (vector embedding)
This commit is contained in:
cybermaggedon 2026-03-09 10:53:44 +00:00 • committed by GitHub
parent 4fa7cc7d7c
commit f2ae0e8623
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
65 changed files with 1339 additions and 1292 deletions
Download patch file Download diff file Expand all files Collapse all files

12
trustgraph-base/trustgraph/api/async_flow.py
View file

@ -612,12 +612,12 @@ class AsyncFlowInstance:
print(f"{entity['name']}: {entity['score']}")
```
"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = await self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
request_data = {
"vectors": vectors,
"vector": vector,
"user": user,
"collection": collection,
"limit": limit
@ -810,12 +810,12 @@ class AsyncFlowInstance:
print(f"{match['index_name']}: {match['index_value']} (score: {match['score']})")
```
"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = await self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
request_data = {
"vectors": vectors,
"vector": vector,
"schema_name": schema_name,
"user": user,
"collection": collection,

12
trustgraph-base/trustgraph/api/async_socket_client.py
View file

@ -282,12 +282,12 @@ class AsyncSocketFlowInstance:
async def graph_embeddings_query(self, text: str, user: str, collection: str, limit: int = 10, **kwargs):
"""Query graph embeddings for semantic search"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = await self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
request = {
"vectors": vectors,
"vector": vector,
"user": user,
"collection": collection,
"limit": limit
@ -352,12 +352,12 @@ class AsyncSocketFlowInstance:
limit: int = 10, **kwargs
):
"""Query row embeddings for semantic search on structured data"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = await self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
request = {
"vectors": vectors,
"vector": vector,
"schema_name": schema_name,
"user": user,
"collection": collection,

18
trustgraph-base/trustgraph/api/flow.py
View file

@ -602,13 +602,13 @@ class FlowInstance:
```
"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
# Query graph embeddings for semantic search
input = {
"vectors": vectors,
"vector": vector,
"user": user,
"collection": collection,
"limit": limit
@ -648,13 +648,13 @@ class FlowInstance:
```
"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
# Query document embeddings for semantic search
input = {
"vectors": vectors,
"vector": vector,
"user": user,
"collection": collection,
"limit": limit
@ -1362,13 +1362,13 @@ class FlowInstance:
```
"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
# Query row embeddings for semantic search
input = {
"vectors": vectors,
"vector": vector,
"schema_name": schema_name,
"user": user,
"collection": collection,

18
trustgraph-base/trustgraph/api/socket_client.py
View file

@ -649,12 +649,12 @@ class SocketFlowInstance:
)
```
"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
request = {
"vectors": vectors,
"vector": vector,
"user": user,
"collection": collection,
"limit": limit
@ -698,12 +698,12 @@ class SocketFlowInstance:
# results contains {"chunk_ids": ["doc1/p0/c0", ...]}
```
"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
request = {
"vectors": vectors,
"vector": vector,
"user": user,
"collection": collection,
"limit": limit
@ -936,12 +936,12 @@ class SocketFlowInstance:
)
```
"""
# First convert text to embeddings vectors
# First convert text to embedding vector
emb_result = self.embeddings(texts=[text])
vectors = emb_result.get("vectors", [[]])[0]
vector = emb_result.get("vectors", [[]])[0]
request = {
"vectors": vectors,
"vector": vector,
"schema_name": schema_name,
"user": user,
"collection": collection,