Skip to content

Commit 6506528

Browse files
pamelafoxpamelafox
committed
Merge branch 'main' into gpt4omini
2 parents d1599da + 88f987e commit 6506528

File tree

97 files changed

+228
-27
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

97 files changed

+228
-27
lines changed

‎.azdo/pipelines/azure-dev.yml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -59,6 +59,7 @@ steps:
5959
AZURE_SEARCH_QUERY_LANGUAGE: $(AZURE_SEARCH_QUERY_LANGUAGE)
6060
AZURE_SEARCH_QUERY_SPELLER: $(AZURE_SEARCH_QUERY_SPELLER)
6161
AZURE_SEARCH_SEMANTIC_RANKER: $(AZURE_SEARCH_SEMANTIC_RANKER)
62+
AZURE_SEARCH_QUERY_REWRITING: $(AZURE_SEARCH_QUERY_REWRITING)
6263
AZURE_STORAGE_ACCOUNT: $(AZURE_STORAGE_ACCOUNT)
6364
AZURE_STORAGE_RESOURCE_GROUP: $(AZURE_STORAGE_RESOURCE_GROUP)
6465
AZURE_STORAGE_SKU: $(AZURE_STORAGE_SKU)

‎.github/workflows/azure-dev.yml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -49,6 +49,7 @@ jobs:
4949
AZURE_SEARCH_QUERY_LANGUAGE: ${{ vars.AZURE_SEARCH_QUERY_LANGUAGE }}
5050
AZURE_SEARCH_QUERY_SPELLER: ${{ vars.AZURE_SEARCH_QUERY_SPELLER }}
5151
AZURE_SEARCH_SEMANTIC_RANKER: ${{ vars.AZURE_SEARCH_SEMANTIC_RANKER }}
52+
AZURE_SEARCH_QUERY_REWRITING: ${{ vars.AZURE_SEARCH_QUERY_REWRITING }}
5253
AZURE_STORAGE_ACCOUNT: ${{ vars.AZURE_STORAGE_ACCOUNT }}
5354
AZURE_STORAGE_RESOURCE_GROUP: ${{ vars.AZURE_STORAGE_RESOURCE_GROUP }}
5455
AZURE_STORAGE_SKU: ${{ vars.AZURE_STORAGE_SKU }}

‎README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -84,7 +84,7 @@ The repo includes sample data so it's ready to try end to end. In this sample ap
8484
Pricing varies per region and usage, so it isn't possible to predict exact costs for your usage.
8585
However, you can try the [Azure pricing calculator](https://azure.com/e/e3490de2372a4f9b909b0d032560e41b) for the resources below.
8686

87-
- Azure Container Apps: Default host for app deployment as of 10/28/2024. See more details in [the ACA deployment guide](docs/azure_container_apps.md). Consumption plan with 1 CPU core, 2.0 GB RAM. Pricing with Pay-as-You-Go. [Pricing](https://azure.microsoft.com/pricing/details/container-apps/)
87+
- Azure Container Apps: Default host for app deployment as of 10/28/2024. See more details in [the ACA deployment guide](docs/azure_container_apps.md). Consumption plan with 1 CPU core, 2 GB RAM, minimum of 0 replicas. Pricing with Pay-as-You-Go. [Pricing](https://azure.microsoft.com/pricing/details/container-apps/)
8888
- Azure Container Registry: Basic tier. [Pricing](https://azure.microsoft.com/pricing/details/container-registry/)
8989
- Azure App Service: Only provisioned if you deploy to Azure App Service following [the App Service deployment guide](docs/azure_app_service.md). Basic Tier with 1 CPU core, 1.75 GB RAM. Pricing per hour. [Pricing](https://azure.microsoft.com/pricing/details/app-service/linux/)
9090
- Azure OpenAI: Standard tier, GPT and Ada models. Pricing per 1K tokens used, and at least 1K tokens are used per question. [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/)

‎app/backend/app.py

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -69,6 +69,7 @@
6969
CONFIG_INGESTER,
7070
CONFIG_LANGUAGE_PICKER_ENABLED,
7171
CONFIG_OPENAI_CLIENT,
72+
CONFIG_QUERY_REWRITING_ENABLED,
7273
CONFIG_SEARCH_CLIENT,
7374
CONFIG_SEMANTIC_RANKER_DEPLOYED,
7475
CONFIG_SPEECH_INPUT_ENABLED,
@@ -291,6 +292,7 @@ def config():
291292
{
292293
"showGPT4VOptions": current_app.config[CONFIG_GPT4V_DEPLOYED],
293294
"showSemanticRankerOption": current_app.config[CONFIG_SEMANTIC_RANKER_DEPLOYED],
295+
"showQueryRewritingOption": current_app.config[CONFIG_QUERY_REWRITING_ENABLED],
294296
"showVectorOption": current_app.config[CONFIG_VECTOR_SEARCH_ENABLED],
295297
"showUserUpload": current_app.config[CONFIG_USER_UPLOAD_ENABLED],
296298
"showLanguagePicker": current_app.config[CONFIG_LANGUAGE_PICKER_ENABLED],
@@ -453,6 +455,7 @@ async def setup_clients():
453455
AZURE_SEARCH_QUERY_LANGUAGE = os.getenv("AZURE_SEARCH_QUERY_LANGUAGE") or "en-us"
454456
AZURE_SEARCH_QUERY_SPELLER = os.getenv("AZURE_SEARCH_QUERY_SPELLER") or "lexicon"
455457
AZURE_SEARCH_SEMANTIC_RANKER = os.getenv("AZURE_SEARCH_SEMANTIC_RANKER", "free").lower()
458+
AZURE_SEARCH_QUERY_REWRITING = os.getenv("AZURE_SEARCH_QUERY_REWRITING", "false").lower()
456459

457460
AZURE_SPEECH_SERVICE_ID = os.getenv("AZURE_SPEECH_SERVICE_ID")
458461
AZURE_SPEECH_SERVICE_LOCATION = os.getenv("AZURE_SPEECH_SERVICE_LOCATION")
@@ -634,6 +637,9 @@ async def setup_clients():
634637

635638
current_app.config[CONFIG_GPT4V_DEPLOYED] = bool(USE_GPT4V)
636639
current_app.config[CONFIG_SEMANTIC_RANKER_DEPLOYED] = AZURE_SEARCH_SEMANTIC_RANKER != "disabled"
640+
current_app.config[CONFIG_QUERY_REWRITING_ENABLED] = (
641+
AZURE_SEARCH_QUERY_REWRITING == "true" and AZURE_SEARCH_SEMANTIC_RANKER != "disabled"
642+
)
637643
current_app.config[CONFIG_VECTOR_SEARCH_ENABLED] = os.getenv("USE_VECTORS", "").lower() != "false"
638644
current_app.config[CONFIG_USER_UPLOAD_ENABLED] = bool(USE_USER_UPLOAD)
639645
current_app.config[CONFIG_LANGUAGE_PICKER_ENABLED] = ENABLE_LANGUAGE_PICKER

‎app/backend/approaches/approach.py

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -149,6 +149,7 @@ async def search(
149149
use_semantic_captions: bool,
150150
minimum_search_score: Optional[float],
151151
minimum_reranker_score: Optional[float],
152+
use_query_rewriting: Optional[bool] = None,
152153
) -> List[Document]:
153154
search_text = query_text if use_text_search else ""
154155
search_vectors = vectors if use_vector_search else []
@@ -158,6 +159,7 @@ async def search(
158159
filter=filter,
159160
top=top,
160161
query_caption="extractive|highlight-false" if use_semantic_captions else None,
162+
query_rewrites="generative" if use_query_rewriting else None,
161163
vector_queries=search_vectors,
162164
query_type=QueryType.SEMANTIC,
163165
query_language=self.query_language,

‎app/backend/approaches/chatreadretrieveread.py

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -89,6 +89,7 @@ async def run_until_final_call(
8989
use_vector_search = overrides.get("retrieval_mode") in ["vectors", "hybrid", None]
9090
use_semantic_ranker = True if overrides.get("semantic_ranker") else False
9191
use_semantic_captions = True if overrides.get("semantic_captions") else False
92+
use_query_rewriting = True if overrides.get("query_rewriting") else False
9293
top = overrides.get("top", 3)
9394
minimum_search_score = overrides.get("minimum_search_score", 0.0)
9495
minimum_reranker_score = overrides.get("minimum_reranker_score", 0.0)
@@ -147,6 +148,7 @@ async def run_until_final_call(
147148
use_semantic_captions,
148149
minimum_search_score,
149150
minimum_reranker_score,
151+
use_query_rewriting,
150152
)
151153

152154
# STEP 3: Generate a contextual and content specific answer using the search results and chat history
@@ -190,6 +192,7 @@ async def run_until_final_call(
190192
{
191193
"use_semantic_captions": use_semantic_captions,
192194
"use_semantic_ranker": use_semantic_ranker,
195+
"use_query_rewriting": use_query_rewriting,
193196
"top": top,
194197
"filter": filter,
195198
"use_vector_search": use_vector_search,

‎app/backend/approaches/chatreadretrievereadvision.py

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -81,6 +81,7 @@ async def run_until_final_call(
8181
use_text_search = overrides.get("retrieval_mode") in ["text", "hybrid", None]
8282
use_vector_search = overrides.get("retrieval_mode") in ["vectors", "hybrid", None]
8383
use_semantic_ranker = True if overrides.get("semantic_ranker") else False
84+
use_query_rewriting = True if overrides.get("query_rewriting") else False
8485
use_semantic_captions = True if overrides.get("semantic_captions") else False
8586
top = overrides.get("top", 3)
8687
minimum_search_score = overrides.get("minimum_search_score", 0.0)
@@ -151,6 +152,7 @@ async def run_until_final_call(
151152
use_semantic_captions,
152153
minimum_search_score,
153154
minimum_reranker_score,
155+
use_query_rewriting,
154156
)
155157

156158
# STEP 3: Generate a contextual and content specific answer using the search results and chat history
@@ -207,6 +209,7 @@ async def run_until_final_call(
207209
{
208210
"use_semantic_captions": use_semantic_captions,
209211
"use_semantic_ranker": use_semantic_ranker,
212+
"use_query_rewriting": use_query_rewriting,
210213
"top": top,
211214
"filter": filter,
212215
"vector_fields": vector_fields,

‎app/backend/approaches/retrievethenread.py

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -67,6 +67,7 @@ async def run(
6767
use_text_search = overrides.get("retrieval_mode") in ["text", "hybrid", None]
6868
use_vector_search = overrides.get("retrieval_mode") in ["vectors", "hybrid", None]
6969
use_semantic_ranker = True if overrides.get("semantic_ranker") else False
70+
use_query_rewriting = True if overrides.get("query_rewriting") else False
7071
use_semantic_captions = True if overrides.get("semantic_captions") else False
7172
top = overrides.get("top", 3)
7273
minimum_search_score = overrides.get("minimum_search_score", 0.0)
@@ -89,6 +90,7 @@ async def run(
8990
use_semantic_captions,
9091
minimum_search_score,
9192
minimum_reranker_score,
93+
use_query_rewriting,
9294
)
9395

9496
# Process results
@@ -118,6 +120,7 @@ async def run(
118120
{
119121
"use_semantic_captions": use_semantic_captions,
120122
"use_semantic_ranker": use_semantic_ranker,
123+
"use_query_rewriting": use_query_rewriting,
121124
"top": top,
122125
"filter": filter,
123126
"use_vector_search": use_vector_search,

‎app/backend/approaches/retrievethenreadvision.py

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -76,6 +76,7 @@ async def run(
7676
use_text_search = overrides.get("retrieval_mode") in ["text", "hybrid", None]
7777
use_vector_search = overrides.get("retrieval_mode") in ["vectors", "hybrid", None]
7878
use_semantic_ranker = True if overrides.get("semantic_ranker") else False
79+
use_query_rewriting = True if overrides.get("query_rewriting") else False
7980
use_semantic_captions = True if overrides.get("semantic_captions") else False
8081
top = overrides.get("top", 3)
8182
minimum_search_score = overrides.get("minimum_search_score", 0.0)
@@ -108,6 +109,7 @@ async def run(
108109
use_semantic_captions,
109110
minimum_search_score,
110111
minimum_reranker_score,
112+
use_query_rewriting,
111113
)
112114

113115
# Process results
@@ -145,6 +147,7 @@ async def run(
145147
{
146148
"use_semantic_captions": use_semantic_captions,
147149
"use_semantic_ranker": use_semantic_ranker,
150+
"use_query_rewriting": use_query_rewriting,
148151
"top": top,
149152
"filter": filter,
150153
"vector_fields": vector_fields,

‎app/backend/config.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,7 @@
1010
CONFIG_AUTH_CLIENT = "auth_client"
1111
CONFIG_GPT4V_DEPLOYED = "gpt4v_deployed"
1212
CONFIG_SEMANTIC_RANKER_DEPLOYED = "semantic_ranker_deployed"
13+
CONFIG_QUERY_REWRITING_ENABLED = "query_rewriting_enabled"
1314
CONFIG_VECTOR_SEARCH_ENABLED = "vector_search_enabled"
1415
CONFIG_SEARCH_CLIENT = "search_client"
1516
CONFIG_OPENAI_CLIENT = "openai_client"

0 commit comments

Comments
 (0)