-
Notifications
You must be signed in to change notification settings - Fork 5
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
frontend: Add feedback reaction buttons and improve chat history hand…
…ling Signed-off-by: error9098x <[email protected]>
- Loading branch information
1 parent
e2af48f
commit 56c1b1e
Showing
4 changed files
with
172 additions
and
89 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
56c1b1e
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
===================================
==> Dataset: EDA Corpus
==> Running tests for agent-retriever
/home/luarss/actions-runner/_work/ORAssistant/ORAssistant/evaluation/.venv/lib/python3.12/site-packages/deepeval/init.py:49: UserWarning: You are using deepeval version 1.4.9, however version 2.0.5 is available. You should consider upgrading via the "pip install --upgrade deepeval" command.
warnings.warn(
Fetching 2 files: 0%| | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 50%|█████ | 1/2 [00:00<00:00, 4.45it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 8.89it/s]
Evaluating: 0%| | 0/100 [00:00<?, ?it/s]
Evaluating: 1%| | 1/100 [00:13<21:27, 13.00s/it]
Evaluating: 2%|▏ | 2/100 [00:24<19:32, 11.96s/it]
Evaluating: 3%|▎ | 3/100 [00:36<19:39, 12.16s/it]
Evaluating: 4%|▍ | 4/100 [00:46<17:43, 11.08s/it]
Evaluating: 5%|▌ | 5/100 [00:56<17:24, 11.00s/it]
Evaluating: 6%|▌ | 6/100 [01:08<17:18, 11.05s/it]
Evaluating: 7%|▋ | 7/100 [01:20<18:02, 11.64s/it]
Evaluating: 8%|▊ | 8/100 [01:32<17:49, 11.62s/it]
Evaluating: 9%|▉ | 9/100 [01:44<17:51, 11.77s/it]
Evaluating: 10%|█ | 10/100 [01:58<18:34, 12.39s/it]
Evaluating: 11%|█ | 11/100 [02:13<19:28, 13.13s/it]
Evaluating: 12%|█▏ | 12/100 [02:25<19:05, 13.02s/it]
Evaluating: 13%|█▎ | 13/100 [02:37<18:18, 12.62s/it]
Evaluating: 14%|█▍ | 14/100 [02:48<17:24, 12.15s/it]
Evaluating: 15%|█▌ | 15/100 [03:00<17:05, 12.06s/it]
Evaluating: 16%|█▌ | 16/100 [03:10<16:00, 11.44s/it]
Evaluating: 17%|█▋ | 17/100 [03:22<15:54, 11.49s/it]
Evaluating: 18%|█▊ | 18/100 [03:32<15:13, 11.14s/it]
Evaluating: 19%|█▉ | 19/100 [03:42<14:43, 10.91s/it]
Evaluating: 20%|██ | 20/100 [03:53<14:27, 10.84s/it]
Evaluating: 21%|██ | 21/100 [04:05<14:31, 11.03s/it]
Evaluating: 22%|██▏ | 22/100 [04:16<14:28, 11.13s/it]
Evaluating: 23%|██▎ | 23/100 [04:26<13:57, 10.88s/it]
Evaluating: 24%|██▍ | 24/100 [04:36<13:25, 10.59s/it]
Evaluating: 25%|██▌ | 25/100 [04:47<13:20, 10.68s/it]
Evaluating: 26%|██▌ | 26/100 [04:56<12:42, 10.31s/it]
Evaluating: 27%|██▋ | 27/100 [05:08<12:57, 10.66s/it]
Evaluating: 28%|██▊ | 28/100 [05:19<12:49, 10.69s/it]
Evaluating: 29%|██▉ | 29/100 [05:29<12:29, 10.55s/it]
Evaluating: 30%|███ | 30/100 [05:40<12:39, 10.85s/it]
Evaluating: 31%|███ | 31/100 [05:51<12:13, 10.64s/it]
Evaluating: 32%|███▏ | 32/100 [06:01<12:06, 10.69s/it]
Evaluating: 33%|███▎ | 33/100 [06:13<12:14, 10.97s/it]
Evaluating: 34%|███▍ | 34/100 [06:24<12:06, 11.01s/it]
Evaluating: 35%|███▌ | 35/100 [06:37<12:24, 11.46s/it]
Evaluating: 36%|███▌ | 36/100 [06:47<11:53, 11.15s/it]
Evaluating: 37%|███▋ | 37/100 [06:58<11:33, 11.01s/it]
Evaluating: 38%|███▊ | 38/100 [07:08<11:05, 10.74s/it]
Evaluating: 39%|███▉ | 39/100 [07:18<10:43, 10.56s/it]
Evaluating: 40%|████ | 40/100 [07:28<10:30, 10.50s/it]
Evaluating: 41%|████ | 41/100 [07:39<10:29, 10.68s/it]
Evaluating: 42%|████▏ | 42/100 [07:50<10:24, 10.77s/it]
Evaluating: 43%|████▎ | 43/100 [08:01<10:13, 10.77s/it]
Evaluating: 44%|████▍ | 44/100 [08:12<10:11, 10.91s/it]
Evaluating: 45%|████▌ | 45/100 [08:25<10:19, 11.27s/it]
Evaluating: 46%|████▌ | 46/100 [08:36<10:18, 11.45s/it]
Evaluating: 47%|████▋ | 47/100 [08:48<10:16, 11.63s/it]
Evaluating: 48%|████▊ | 48/100 [08:59<09:55, 11.45s/it]
Evaluating: 49%|████▉ | 49/100 [09:13<10:17, 12.11s/it]
Evaluating: 50%|█████ | 50/100 [09:26<10:13, 12.26s/it]
Evaluating: 51%|█████ | 51/100 [09:36<09:24, 11.51s/it]
Evaluating: 52%|█████▏ | 52/100 [09:48<09:28, 11.84s/it]
Evaluating: 53%|█████▎ | 53/100 [09:59<08:59, 11.48s/it]
Evaluating: 54%|█████▍ | 54/100 [10:10<08:43, 11.38s/it]
Evaluating: 55%|█████▌ | 55/100 [10:21<08:32, 11.39s/it]
Evaluating: 56%|█████▌ | 56/100 [10:31<08:04, 11.01s/it]
Evaluating: 57%|█████▋ | 57/100 [10:42<07:46, 10.84s/it]
Evaluating: 58%|█████▊ | 58/100 [10:52<07:32, 10.77s/it]
Evaluating: 59%|█████▉ | 59/100 [11:04<07:27, 10.91s/it]
Evaluating: 60%|██████ | 60/100 [11:15<07:22, 11.06s/it]
Evaluating: 61%|██████ | 61/100 [11:27<07:18, 11.23s/it]
Evaluating: 62%|██████▏ | 62/100 [11:37<06:57, 10.99s/it]
Evaluating: 63%|██████▎ | 63/100 [11:48<06:42, 10.88s/it]
Evaluating: 64%|██████▍ | 64/100 [11:56<06:07, 10.21s/it]
Evaluating: 65%|██████▌ | 65/100 [12:05<05:38, 9.67s/it]
Evaluating: 66%|██████▌ | 66/100 [12:16<05:48, 10.25s/it]
Evaluating: 67%|██████▋ | 67/100 [12:28<05:46, 10.50s/it]
Evaluating: 68%|██████▊ | 68/100 [12:44<06:34, 12.31s/it]
Evaluating: 69%|██████▉ | 69/100 [12:58<06:31, 12.64s/it]
Evaluating: 70%|███████ | 70/100 [13:12<06:33, 13.13s/it]
Evaluating: 71%|███████ | 71/100 [13:22<05:55, 12.25s/it]
Evaluating: 72%|███████▏ | 72/100 [13:31<05:17, 11.33s/it]
Evaluating: 73%|███████▎ | 73/100 [13:43<05:07, 11.39s/it]
Evaluating: 74%|███████▍ | 74/100 [13:54<04:54, 11.31s/it]
Evaluating: 75%|███████▌ | 75/100 [14:06<04:47, 11.50s/it]
Evaluating: 76%|███████▌ | 76/100 [14:18<04:41, 11.71s/it]
Evaluating: 77%|███████▋ | 77/100 [14:31<04:40, 12.18s/it]
Evaluating: 78%|███████▊ | 78/100 [14:43<04:26, 12.13s/it]
Evaluating: 79%|███████▉ | 79/100 [14:53<04:00, 11.46s/it]
Evaluating: 80%|████████ | 80/100 [15:04<03:45, 11.26s/it]
Evaluating: 81%|████████ | 81/100 [15:15<03:31, 11.13s/it]
Evaluating: 82%|████████▏ | 82/100 [15:25<03:15, 10.88s/it]
Evaluating: 83%|████████▎ | 83/100 [15:35<02:59, 10.58s/it]
Evaluating: 84%|████████▍ | 84/100 [15:47<02:55, 10.98s/it]
Evaluating: 85%|████████▌ | 85/100 [15:56<02:36, 10.46s/it]
Evaluating: 86%|████████▌ | 86/100 [16:08<02:32, 10.91s/it]
Evaluating: 87%|████████▋ | 87/100 [16:18<02:19, 10.72s/it]
Evaluating: 88%|████████▊ | 88/100 [16:30<02:10, 10.86s/it]
Evaluating: 89%|████████▉ | 89/100 [16:42<02:05, 11.40s/it]
Evaluating: 90%|█████████ | 90/100 [16:55<01:56, 11.69s/it]
Evaluating: 91%|█████████ | 91/100 [17:08<01:50, 12.28s/it]
Evaluating: 92%|█████████▏| 92/100 [17:21<01:38, 12.31s/it]
Evaluating: 93%|█████████▎| 93/100 [17:31<01:21, 11.71s/it]
Evaluating: 94%|█████████▍| 94/100 [17:41<01:06, 11.13s/it]
Evaluating: 95%|█████████▌| 95/100 [17:51<00:54, 10.87s/it]
Evaluating: 96%|█████████▌| 96/100 [18:01<00:42, 10.72s/it]
Evaluating: 97%|█████████▋| 97/100 [18:12<00:32, 10.84s/it]
Evaluating: 98%|█████████▊| 98/100 [18:25<00:22, 11.23s/it]
Evaluating: 99%|█████████▉| 99/100 [18:35<00:10, 10.92s/it]
Evaluating: 100%|██████████| 100/100 [18:46<00:00, 11.14s/it]
Evaluating: 100%|██████████| 100/100 [18:46<00:00, 11.27s/it]
✨ You're running DeepEval's latest Contextual Precision Metric! (using
gemini-1.5-pro-002, strict=False, async_mode=True)...
✨ You're running DeepEval's latest Contextual Recall Metric! (using
gemini-1.5-pro-002, strict=False, async_mode=True)...
✨ You're running DeepEval's latest Hallucination Metric! (using
gemini-1.5-pro-002, strict=False, async_mode=True)...
Evaluating 100 test case(s) in parallel: | | 0% (0/100) [Time Taken: 00:00, ?test case/s]
‼️ Friendly reminder 😇: You can also run evaluations with ALL of deepeval's
Evaluating 100 test case(s) in parallel: | | 1% (1/100) [Time Taken: 00:10, 10.43s/test case]
Evaluating 100 test case(s) in parallel: |▏ | 2% (2/100) [Time Taken: 00:11, 4.92s/test case]
Evaluating 100 test case(s) in parallel: |▎ | 3% (3/100) [Time Taken: 00:11, 2.78s/test case]
Evaluating 100 test case(s) in parallel: |▍ | 4% (4/100) [Time Taken: 00:11, 1.77s/test case]
Evaluating 100 test case(s) in parallel: |▌ | 5% (5/100) [Time Taken: 00:14, 1.91s/test case]
Evaluating 100 test case(s) in parallel: |▊ | 8% (8/100) [Time Taken: 00:14, 1.16test case/s]
Evaluating 100 test case(s) in parallel: |█ | 10% (10/100) [Time Taken: 00:15, 1.49test case/s]
Evaluating 100 test case(s) in parallel: |█ | 11% (11/100) [Time Taken: 00:15, 1.80test case/s]
Evaluating 100 test case(s) in parallel: |█▏ | 12% (12/100) [Time Taken: 00:15, 2.16test case/s]
Evaluating 100 test case(s) in parallel: |█▎ | 13% (13/100) [Time Taken: 00:15, 2.56test case/s]
Evaluating 100 test case(s) in parallel: |█▍ | 14% (14/100) [Time Taken: 00:15, 3.02test case/s]
Evaluating 100 test case(s) in parallel: |█▊ | 18% (18/100) [Time Taken: 00:16, 5.43test case/s]
Evaluating 100 test case(s) in parallel: |█▉ | 19% (19/100) [Time Taken: 00:16, 5.29test case/s]
Evaluating 100 test case(s) in parallel: |██▏ | 22% (22/100) [Time Taken: 00:16, 7.98test case/s]
Evaluating 100 test case(s) in parallel: |██▌ | 26% (26/100) [Time Taken: 00:17, 8.52test case/s]
Evaluating 100 test case(s) in parallel: |██▉ | 29% (29/100) [Time Taken: 00:17, 10.99test case/s]
Evaluating 100 test case(s) in parallel: |███▎ | 33% (33/100) [Time Taken: 00:17, 9.39test case/s]
Evaluating 100 test case(s) in parallel: |███▌ | 35% (35/100) [Time Taken: 00:18, 6.12test case/s]
Evaluating 100 test case(s) in parallel: |███▋ | 37% (37/100) [Time Taken: 00:20, 2.51test case/s]
Evaluating 100 test case(s) in parallel: |███▊ | 38% (38/100) [Time Taken: 00:21, 2.24test case/s]
Evaluating 100 test case(s) in parallel: |███▉ | 39% (39/100) [Time Taken: 00:21, 2.50test case/s]
Evaluating 100 test case(s) in parallel: |████▏ | 42% (42/100) [Time Taken: 00:21, 4.00test case/s]
Evaluating 100 test case(s) in parallel: |████▍ | 44% (44/100) [Time Taken: 00:22, 4.37test case/s]
Evaluating 100 test case(s) in parallel: |████▌ | 46% (46/100) [Time Taken: 00:22, 4.83test case/s]
Evaluating 100 test case(s) in parallel: |████▋ | 47% (47/100) [Time Taken: 00:22, 5.05test case/s]
Evaluating 100 test case(s) in parallel: |████▉ | 49% (49/100) [Time Taken: 00:22, 6.42test case/s]
Evaluating 100 test case(s) in parallel: |█████ | 51% (51/100) [Time Taken: 00:22, 7.46test case/s]
Evaluating 100 test case(s) in parallel: |█████▎ | 53% (53/100) [Time Taken: 00:23, 9.14test case/s]
Evaluating 100 test case(s) in parallel: |█████▌ | 55% (55/100) [Time Taken: 00:23, 7.38test case/s]
Evaluating 100 test case(s) in parallel: |█████▋ | 57% (57/100) [Time Taken: 00:23, 5.85test case/s]
Evaluating 100 test case(s) in parallel: |█████▉ | 59% (59/100) [Time Taken: 00:24, 7.02test case/s]
Evaluating 100 test case(s) in parallel: |██████ | 61% (61/100) [Time Taken: 00:24, 5.89test case/s]
Evaluating 100 test case(s) in parallel: |██████▏ | 62% (62/100) [Time Taken: 00:24, 4.93test case/s]
Evaluating 100 test case(s) in parallel: |██████▍ | 64% (64/100) [Time Taken: 00:25, 5.90test case/s]
Evaluating 100 test case(s) in parallel: |██████▌ | 65% (65/100) [Time Taken: 00:25, 6.10test case/s]
Evaluating 100 test case(s) in parallel: |██████▌ | 66% (66/100) [Time Taken: 00:25, 4.69test case/s]
Evaluating 100 test case(s) in parallel: |██████▋ | 67% (67/100) [Time Taken: 00:25, 4.51test case/s]
Evaluating 100 test case(s) in parallel: |██████▊ | 68% (68/100) [Time Taken: 00:26, 3.75test case/s]
Evaluating 100 test case(s) in parallel: |██████▉ | 69% (69/100) [Time Taken: 00:26, 3.80test case/s]
Evaluating 100 test case(s) in parallel: |███████ | 70% (70/100) [Time Taken: 00:26, 3.84test case/s]
Evaluating 100 test case(s) in parallel: |███████ | 71% (71/100) [Time Taken: 00:27, 3.79test case/s]
Evaluating 100 test case(s) in parallel: |███████▏ | 72% (72/100) [Time Taken: 00:27, 3.47test case/s]
Evaluating 100 test case(s) in parallel: |███████▎ | 73% (73/100) [Time Taken: 00:28, 2.57test case/s]
Evaluating 100 test case(s) in parallel: |███████▍ | 74% (74/100) [Time Taken: 00:28, 2.53test case/s]
Evaluating 100 test case(s) in parallel: |███████▌ | 75% (75/100) [Time Taken: 00:28, 2.88test case/s]
Evaluating 100 test case(s) in parallel: |███████▋ | 77% (77/100) [Time Taken: 00:28, 4.10test case/s]
Evaluating 100 test case(s) in parallel: |███████▊ | 78% (78/100) [Time Taken: 00:29, 4.62test case/s]
Evaluating 100 test case(s) in parallel: |███████▉ | 79% (79/100) [Time Taken: 00:29, 4.98test case/s]
Evaluating 100 test case(s) in parallel: |████████ | 81% (81/100) [Time Taken: 00:29, 6.61test case/s]
Evaluating 100 test case(s) in parallel: |████████▏ | 82% (82/100) [Time Taken: 00:29, 4.92test case/s]
Evaluating 100 test case(s) in parallel: |████████▎ | 83% (83/100) [Time Taken: 00:29, 5.07test case/s]
Evaluating 100 test case(s) in parallel: |████████▍ | 84% (84/100) [Time Taken: 00:30, 4.89test case/s]
Evaluating 100 test case(s) in parallel: |████████▌ | 85% (85/100) [Time Taken: 00:30, 4.23test case/s]
Evaluating 100 test case(s) in parallel: |████████▌ | 86% (86/100) [Time Taken: 00:31, 2.21test case/s]
Evaluating 100 test case(s) in parallel: |████████▊ | 88% (88/100) [Time Taken: 00:31, 3.10test case/s]
Evaluating 100 test case(s) in parallel: |████████▉ | 89% (89/100) [Time Taken: 00:32, 3.25test case/s]
Evaluating 100 test case(s) in parallel: |█████████ | 91% (91/100) [Time Taken: 00:32, 4.55test case/s]
Evaluating 100 test case(s) in parallel: |█████████▎| 93% (93/100) [Time Taken: 00:32, 3.96test case/s]
Evaluating 100 test case(s) in parallel: |█████████▌| 95% (95/100) [Time Taken: 00:33, 5.03test case/s]
Evaluating 100 test case(s) in parallel: |█████████▌| 96% (96/100) [Time Taken: 00:33, 4.43test case/s]
Evaluating 100 test case(s) in parallel: |█████████▊| 98% (98/100) [Time Taken: 00:34, 2.82test case/s]
Evaluating 100 test case(s) in parallel: |█████████▉| 99% (99/100) [Time Taken: 00:39, 1.27s/test case]
Evaluating 100 test case(s) in parallel: |██████████|100% (100/100) [Time Taken: 00:55, 4.52s/test case]
Evaluating 100 test case(s) in parallel: |██████████|100% (100/100) [Time Taken: 00:55, 1.82test case/s]
✓ Tests finished 🎉! Run 'deepeval login' to save and analyze evaluation results
on Confident AI.
metrics directly on Confident AI instead.
Average Metric Scores:
Contextual Precision 0.7070555555555554
Contextual Recall 0.8928333333333334
Hallucination 0.5250240800865801
Metric Passrates:
Contextual Precision 0.67
Contextual Recall 0.86
Hallucination 0.6