Skip to content

Commit e8398db

Browse files
vrushankportkeyvrushankportkey
authored
Merge branch 'main' into model-catalog-v4
2 parents 4016b8b + d3f6a32 commit e8398db

File tree

11 files changed

+900
-10
lines changed

11 files changed

+900
-10
lines changed

‎changelog/data-service.mdx‎

Lines changed: 297 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,297 @@
1+
---
2+
title: "Data Service"
3+
sidebarTitle: "Data Service [1.2.4]"
4+
---
5+
6+
<Update label="1.2.4" description="2025-06-17">
7+
## v1.2.4
8+
---
9+
10+
### Fixes and Improvements
11+
- Fixed issue with custom batches missing cost calculation for some provider models
12+
</Update>
13+
14+
<Update label="1.2.3" description="2025-06-17">
15+
## v1.2.3
16+
---
17+
18+
### Fine-tuning and Batch Processing
19+
- Added support for configurable `FINETUNE_STATUS_CHECK_INTERVAL` for provider fine-tuning status check operations.
20+
- Added support for configurable `BATCH_STATUS_CHECK_INTERVAL` for provider batch processing status check operations.
21+
- Both values should be in milliseconds. Minimum value is 10000 milliseconds.
22+
- If not provided, will default to 10 seconds.
23+
24+
</Update>
25+
26+
<Update label="1.2.2" description="2025-05-31">
27+
## v1.2.2
28+
---
29+
30+
### Observability
31+
- Added support for below Prometheus Counters
32+
- `batch_count`
33+
- `batch_cost`
34+
- `batch_input_tokens`
35+
- `batch_total_tokens`
36+
- `batch_process_time`
37+
- `batch_success_row_count`
38+
- `batch_failure_row_count`
39+
- `batch_row_count`
40+
- With the below labels
41+
- `provider`
42+
- `type` (provider/custom)
43+
44+
### Fixes and Improvements
45+
- Fixed issue with attributing incorrect created at time stamp for batch processing
46+
- Including error source as `control plane` for control plane failures
47+
</Update>
48+
49+
<Update label="1.2.1" description="2025-05-21">
50+
## v1.2.1
51+
---
52+
53+
### Data exports
54+
- Added support for [Data exports](/api-reference/admin-api/data-plane/logs/log-exports-beta/start-a-log-export) for hybrid deployments.
55+
56+
### Fixes and Improvements
57+
- Fixed issue with custom batches for small batch files
58+
</Update>
59+
60+
<Update label="1.2.0" description="2025-05-17">
61+
## v1.2.0
62+
---
63+
64+
### Custom S3 Support
65+
- Added support for `s3_custom` log store option for batches and fine-tunes.
66+
67+
### Fixes and Improvements
68+
- Fixed issue with STS token generation for AWS.
69+
</Update>
70+
71+
<Update label="1.1.12" description="2025-05-09">
72+
## v1.1.12
73+
---
74+
75+
### Fixes and Improvements
76+
- Fixed issue with cost calculation for custom batches.
77+
</Update>
78+
79+
<Update label="1.1.11" description="2025-05-03">
80+
## v1.1.11
81+
---
82+
83+
### Fixes and Improvements
84+
- Fixed issue where queue remains stuck in a queued state during file validation.
85+
</Update>
86+
87+
88+
<Update label="1.1.10" description="2025-04-21">
89+
## v1.1.10
90+
---
91+
92+
### S3 Upload Improvements
93+
- Added support for passing encryption headers while uploading stream data to S3.
94+
- Added support for both file path and direct value from environment variables for secrets like redis connection.
95+
96+
### Stream Handling
97+
- Improved stream cleanup for validation processes.
98+
</Update>
99+
100+
<Update label="1.1.9" description="2025-04-10">
101+
## v1.1.9
102+
---
103+
104+
### File Handling Fixes
105+
- Fixed issue with extra bytes being added to files during processing.
106+
</Update>
107+
108+
<Update label="1.1.8" description="2025-04-04">
109+
## v1.1.8
110+
---
111+
112+
### File Upload Improvements
113+
- Updated socket timeout for long requests during file uploads to prevent timeouts.
114+
</Update>
115+
116+
<Update label="1.1.7" description="2025-03-28">
117+
## v1.1.7
118+
---
119+
120+
### Fireworks Fine-tuning Support
121+
- Added support for `Fireworks` fine-tuning operations using Version2.
122+
123+
### Batch Processing Improvements
124+
- Included response tokens calculation in provider batch output.
125+
- Fixed file loading in memory issues for better performance.
126+
</Update>
127+
128+
<Update label="1.1.6" description="2025-03-25">
129+
## v1.1.6
130+
---
131+
132+
### S3 SDK Updates
133+
- Upgraded S3 SDK to latest version for fixing issue with S3 streaming.
134+
</Update>
135+
136+
<Update label="1.1.5" description="2025-03-21">
137+
## v1.1.5
138+
---
139+
140+
### Batch Processing Enhancements
141+
- Improved provider batch output handling.
142+
- Added support for custom batch output paths.
143+
- Increased maximum lines for custom batches to 500k and chunk size to 5MB for better performance.
144+
</Update>
145+
146+
<Update label="1.1.4" description="2025-03-20">
147+
## v1.1.4
148+
---
149+
150+
### Vertex Embeddings Batches Support
151+
- Added support for `Vertex` batch embeddings.
152+
153+
### Batch Processing Updates
154+
- Included model information in log objects.
155+
- Implemented custom batch processing output generations.
156+
157+
### Internal POD to POD HTTPS Support
158+
- Added support for internal POD to POD HTTPS communication.
159+
- This can be enabled by mounting a volume with certificate and key.
160+
- `TLS_KEY_PATH` and `TLS_CERT_PATH` environment variables will be used to fetch the certificate and key from the volume.
161+
162+
</Update>
163+
164+
<Update label="1.1.3" description="2025-03-07">
165+
## v1.1.3
166+
---
167+
168+
### Infrastructure Updates
169+
- Streamlined uploaded file location for `Bedrock` operations.
170+
</Update>
171+
172+
<Update label="1.1.2" description="2025-02-27">
173+
## v1.1.2
174+
---
175+
176+
### Vertex Integration
177+
- Added support for `Vertex` provider options for batches.
178+
179+
### Infrastructure Updates
180+
- Implemented cluster mode Redis for queues.
181+
- Updated fine-tune status handling.
182+
</Update>
183+
184+
<Update label="1.1.1" description="2025-02-20">
185+
## v1.1.1
186+
---
187+
188+
### S3 Enhancements
189+
- Made S3 bucket optional for Bedrock batches.
190+
- Added S3 encryption header support for finetunes and batches.
191+
- Implemented SSE file upload support.
192+
193+
### Logging Improvements
194+
- Added filtering for log exports.
195+
- Implemented end limit for log export records.
196+
197+
### Performance Optimizations
198+
- Implemented internal memory cache for better performance.
199+
</Update>
200+
201+
<Update label="1.1.0" description="2025-02-10">
202+
## v1.1.0
203+
---
204+
205+
### Bull Board Integration
206+
- Added Bull Board for visualizing job queues and their status.
207+
208+
### Batch Job Retry Support
209+
- Implemented retry functionality for batch jobs to handle failures gracefully.
210+
211+
### Prometheus Metrics Enhancements
212+
- Added Prometheus metrics for batch jobs and fine-tuning operations.
213+
214+
</Update>
215+
216+
<Update label="1.0.8" description="2025-02-04">
217+
## v1.0.8
218+
---
219+
220+
### Azure Fine-tuning Support
221+
- Added support for `Azure OpeAI` fine-tuning operations.
222+
223+
</Update>
224+
225+
<Update label="1.0.7" description="2025-01-13">
226+
## v1.0.7
227+
---
228+
229+
### Fine-tune v2
230+
- Implemented version 2 of the [fine-tuning](/product/ai-gateway/fine-tuning) functionality.
231+
</Update>
232+
233+
<Update label="1.0.6" description="2024-01-08">
234+
## v1.0.6
235+
---
236+
237+
### Prompt Slug Filter
238+
- Added support for data exports filtering by PromptSlug.
239+
240+
</Update>
241+
242+
<Update label="1.0.5" description="2024-01-06">
243+
## v1.0.5
244+
---
245+
246+
### Batch Processing
247+
- Added provider and custom [Batch] (/product/ai-gateway/batches) processing functionality.
248+
249+
</Update>
250+
251+
<Update label="1.0.4" description="2023-12-17">
252+
## v1.0.4
253+
---
254+
255+
### Code Quality Improvements
256+
- Fixed dynamic port retrieval from environment variables.
257+
</Update>
258+
259+
<Update label="1.0.3" description="2023-11-28">
260+
## v1.0.3
261+
---
262+
263+
### Vision Fine-tuning Support
264+
- Added support for vision fine-tuning validation for OpenAI.
265+
- Implemented S3 bucket support for fine-tunes.
266+
267+
### AWS Integration Improvements
268+
- Fixed assumed role handling for Bedrock fine-tuning dataset URLs.
269+
- Improved S3 bucket path handling for Bedrock fine-tune operations.
270+
- Achieved parity with Enterprise Gateway for data sources.
271+
</Update>
272+
273+
<Update label="1.0.2" description="2023-11-20">
274+
## v1.0.2
275+
---
276+
277+
### Fine-tuning Enhancements
278+
- Added support for OpenAI job start and Fireworks upload.
279+
- Improved handling of chunk type failures with JSON.
280+
</Update>
281+
282+
<Update label="1.0.1" description="2023-10-25">
283+
## v1.0.1
284+
---
285+
286+
### Fireworks Fine-tuning Support
287+
- Added support for Fireworks fine-tuning operations.
288+
289+
</Update>
290+
291+
<Update label="1.0.0" description="2023-10-04">
292+
## v1.0.0
293+
---
294+
295+
### Initial Release
296+
- Base version of the Data Service with core functionality.
297+
</Update>

‎changelog/enterprise.mdx‎

Lines changed: 72 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,83 @@
11
---
22
title: "Enterprise Gateway"
3-
sidebarTitle: "Enterprise Gateway [1.11.2]"
3+
sidebarTitle: "Enterprise Gateway [1.11.6]"
44
---
55

66
<Card title="Schedule Call" href="https://portkey.sh/demo-21" icon="calendar" horizontal>
77
Discuss how Portkey's AI Gateway can enhance your organization's AI infrastructure
88
</Card>
99

10+
<Update label="1.11.6" description="2025-06-21">
11+
## v1.11.6
12+
---
13+
14+
### Provider Updates
15+
- **Groq**: Added support for `service_tier` parameter in the Groq provider configuration
16+
- **Anthropic**: Added support for Anthropic's prompt caching for tool results and tool use
17+
- **Anthropic**: Fixed multi turn tool calling when arguments to the tool call is empty
18+
19+
### Improvements and Fixes
20+
- Fixed an issue with Auth enabled Aws Redis Cache with Password and cluster mode
21+
- Handled Webhook Guardrail errors and return verdict with the correct status and error
22+
23+
</Update>
24+
25+
<Update label="1.11.5" description="2025-06-18">
26+
## v1.11.5
27+
---
28+
29+
### Guardrails
30+
- Added support for metadata keys plugin to enforce metadata keys from the request.
31+
32+
</Update>
33+
34+
35+
<Update label="1.11.4" description="2025-06-17">
36+
## v1.11.4
37+
---
38+
39+
### Provider Updates
40+
- **Bedrock**: Added support for `AssumedRole` for bedrock application inference profiles
41+
- **Bedrock Multimodal Embeddings**: Added support for multimodal embeddings for providers `cohere` and `titan`.
42+
- **Azure Foundry**: Added support for `createTranscription`,`createTranslation`, `imageGeneration`, `batch` and `files` endpoints.
43+
- **Anthropic**: Added Support for computer use tool.
44+
- **Anthropic**: Added support for `file_url` and `mime_type` for `file` content parts in Anthropic requests.
45+
- **VertexAI**: Added support for Gemini/Vertex Thinking mode.
46+
47+
### Cache Improvements
48+
- Added support for Azure Redis with auth modes `EntraID` and `ManagedIdentity`
49+
50+
### Fixes And Improvements
51+
- Improvements for Redis Cache
52+
- Added support for separate username and password for Redis Cache. Use `REDIS_USERNAME` and `REDIS_PASSWORD` environment variables.
53+
- Added support for Azure Redis Cache. Use `CACHE_STORE` with `azure-redis` as value.
54+
- Added support for Managed Identity for Azure Managed Redis.
55+
- You can pass `AZURE_REDIS_AUTH_MODE` and `AZURE_REDIS_MANAGED_CLIENT_ID` for a different auth setup.
56+
- Defaults to `AZURE_AUTH_MODE` and `AZURE_MANAGED_CLIENT_ID` if not provided
57+
- Added support for Entra ID for Azure Redis Cache.
58+
- You can pass `AZURE_REDIS_AUTH_MODE` and `AZURE_REDIS_ENTRA_CLIENT_ID`, `AZURE_REDIS_ENTRA_CLIENT_SECRET`, `AZURE_REDIS_ENTRA_TENANT_ID` for a different auth setup.
59+
- Defaults to `AZURE_AUTH_MODE` and `AZURE_ENTRA_CLIENT_ID`, `AZURE_ENTRA_CLIENT_SECRET`, `AZURE_ENTRA_TENANT_ID` if not provided
60+
- **HTTPS Proxy**
61+
- Added HTTPS Proxy support for all the external calls.
62+
- Pass `HTTPS_PROXY` environment variable to enable this feature.
63+
- Added support for virtual key inclusion for custom log if passed in headers.
64+
- Fixed issue with proxy calls not working with configs for some providers.
65+
66+
</Update>
67+
68+
<Update label="1.11.3" description="2025-06-06">
69+
## v1.11.3
70+
---
71+
72+
### Observability
73+
- Prometheus Metrics are migrated to use endpoints instead of path for all the metrics
74+
75+
### Fixes And Improvements
76+
- Added a global error handler for all the unhandled exceptions to prevent server crashes.
77+
- Updated JWT Plugin to validate `iat` field
78+
79+
</Update>
80+
1081
<Update label="1.11.2" description="2025-06-03">
1182
## v1.11.2
1283
---

0 commit comments

Comments
 (0)