Viewing enriched Twitter post
This guest post from @deepeval shows you how to build better RAG applications by combining LlamaIndex with comprehensive evaluation: 🎯 Use Answer Relevancy, Faithfulness, and Contextual Precision metrics to measure both your retriever and generator components 🔧 Set up… https://t.co/oiI52T58NW
{
"media": [
{
"type": "image",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1940878254954762369/media_0.jpg?",
"filename": "media_0.jpg"
}
],
"nlp": {
"sentiment": "positive",
"topics": [
"RAG applications",
"LlamaIndex",
"evaluation metrics"
],
"entities": [
"@deepeval"
],
"summary": "The tweet promotes a guest post that explains how to improve RAG applications using LlamaIndex and evaluation metrics.",
"language": "en",
"processed_at": "2025-08-07T09:58:22.154841"
}
}{
"data": {
"threaded_conversation_with_injections_v2": {
"instructions": [
{
"type": "TimelineClearCache"
},
{
"type": "TimelineAddEntries",
"entries": [
{
"entryId": "tweet-1940878254954762369",
"sortIndex": "1953485864407400448",
"content": {
"entryType": "TimelineTimelineItem",
"__typename": "TimelineTimelineItem",
"itemContent": {
"itemType": "TimelineTweet",
"__typename": "TimelineTweet",
"tweet_results": {
"result": {
"__typename": "Tweet",
"rest_id": "1940878254954762369",
"has_birdwatch_notes": false,
"core": {
"user_results": {
"result": {
"__typename": "User",
"id": "VXNlcjoxNjA0Mjc4MzU4Mjk2MDU1ODA4",
"rest_id": "1604278358296055808",
"affiliates_highlighted_label": {},
"has_graduated_access": true,
"is_blue_verified": true,
"profile_image_shape": "Circle",
"legacy": {
"can_dm": false,
"can_media_tag": true,
"created_at": "Sun Dec 18 00:52:44 +0000 2022",
"default_profile": true,
"default_profile_image": false,
"description": "Build AI agents over your documents\n\nGithub: https://t.co/HC19j7vMwc\nDocs: https://t.co/QInqg2zksh\nLlamaCloud: https://t.co/yQGTiRSNvj",
"entities": {
"description": {
"urls": [
{
"display_url": "github.com/run-llama/llam…",
"expanded_url": "http://github.com/run-llama/llama_index",
"url": "https://t.co/HC19j7vMwc",
"indices": [
45,
68
]
},
{
"display_url": "docs.llamaindex.ai",
"expanded_url": "http://docs.llamaindex.ai",
"url": "https://t.co/QInqg2zksh",
"indices": [
75,
98
]
},
{
"display_url": "cloud.llamaindex.ai",
"expanded_url": "https://cloud.llamaindex.ai/",
"url": "https://t.co/yQGTiRSNvj",
"indices": [
111,
134
]
}
]
},
"url": {
"urls": [
{
"display_url": "llamaindex.ai",
"expanded_url": "https://www.llamaindex.ai/",
"url": "https://t.co/epzefqQqZx",
"indices": [
0,
23
]
}
]
}
},
"fast_followers_count": 0,
"favourites_count": 1425,
"followers_count": 99661,
"friends_count": 28,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 1571,
"location": "",
"media_count": 1676,
"name": "LlamaIndex 🦙",
"normal_followers_count": 99661,
"pinned_tweet_ids_str": [
"1950285220663742516"
],
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/1604278358296055808/1752258343",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1623505166996742144/n-PNQGgd_normal.jpg",
"profile_interstitial_type": "",
"screen_name": "llama_index",
"statuses_count": 3500,
"translator_type": "none",
"url": "https://t.co/epzefqQqZx",
"verified": false,
"want_retweets": false,
"withheld_in_countries": []
},
"tipjar_settings": {}
}
}
},
"unmention_data": {},
"edit_control": {
"edit_tweet_ids": [
"1940878254954762369"
],
"editable_until_msecs": "1751580010000",
"is_edit_eligible": true,
"edits_remaining": "5"
},
"is_translatable": false,
"views": {
"count": "4830",
"state": "EnabledWithCount"
},
"source": "<a href=\"https://typefully.com/\" rel=\"nofollow\">Typefully</a>",
"note_tweet": {
"is_expandable": true,
"note_tweet_results": {
"result": {
"id": "Tm90ZVR3ZWV0OjE5NDA4NzgyNTQ3NTMzOTg3ODQ=",
"text": "This guest post from @deepeval shows you how to build better RAG applications by combining LlamaIndex with comprehensive evaluation:\n\n🎯 Use Answer Relevancy, Faithfulness, and Contextual Precision metrics to measure both your retriever and generator components\n🔧 Set up systematic testing with LLMTestCase to evaluate your RAG responses against retrieved context\n📊 Run comparative experiments across different models (GPT-3.5, GPT-4o, O1) to optimize performance based on evaluation scores\n⚡ Scale your evaluations with @deepeval's 50+ built-in metrics or create custom metrics for domain-specific requirements\n\nThe tutorial walks through a complete example using LlamaIndex's VectorStoreIndex and shows how low Faithfulness scores can guide you to experiment with different models for better context grounding.\n\nRead the full tutorial with code examples: https://t.co/z1TESzYKpM",
"entity_set": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "llamaindex.ai/blog/evaluatin…",
"expanded_url": "https://www.llamaindex.ai/blog/evaluating-rag-with-deepeval-and-llamaindex?utm_source=socials&utm_medium=li_social",
"url": "https://t.co/z1TESzYKpM",
"indices": [
856,
879
]
}
],
"user_mentions": [
{
"id_str": "1888058644434141184",
"name": "DeepEval",
"screen_name": "deepeval",
"indices": [
21,
30
]
},
{
"id_str": "1888058644434141184",
"name": "DeepEval",
"screen_name": "deepeval",
"indices": [
520,
529
]
}
]
}
}
}
},
"legacy": {
"bookmark_count": 26,
"bookmarked": false,
"created_at": "Thu Jul 03 21:00:10 +0000 2025",
"conversation_id_str": "1940878254954762369",
"display_text_range": [
0,
270
],
"entities": {
"hashtags": [],
"media": [
{
"display_url": "pic.x.com/oiI52T58NW",
"expanded_url": "https://x.com/llama_index/status/1940878254954762369/photo/1",
"id_str": "1940878251477585920",
"indices": [
271,
294
],
"media_key": "3_1940878251477585920",
"media_url_https": "https://pbs.twimg.com/media/Gu9ifIuaUAAMQ9Y.jpg",
"type": "photo",
"url": "https://t.co/oiI52T58NW",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": [
{
"x": 317,
"y": 504,
"h": 131,
"w": 131
},
{
"x": 133,
"y": 61,
"h": 264,
"w": 264
}
]
},
"medium": {
"faces": [
{
"x": 317,
"y": 504,
"h": 131,
"w": 131
},
{
"x": 133,
"y": 61,
"h": 264,
"w": 264
}
]
},
"small": {
"faces": [
{
"x": 199,
"y": 317,
"h": 82,
"w": 82
},
{
"x": 83,
"y": 38,
"h": 166,
"w": 166
}
]
},
"orig": {
"faces": [
{
"x": 317,
"y": 504,
"h": 131,
"w": 131
},
{
"x": 133,
"y": 61,
"h": 264,
"w": 264
}
]
}
},
"sizes": {
"large": {
"h": 1080,
"w": 1080,
"resize": "fit"
},
"medium": {
"h": 1080,
"w": 1080,
"resize": "fit"
},
"small": {
"h": 680,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 1080,
"width": 1080,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1080,
"h": 605
},
{
"x": 0,
"y": 0,
"w": 1080,
"h": 1080
},
{
"x": 67,
"y": 0,
"w": 947,
"h": 1080
},
{
"x": 270,
"y": 0,
"w": 540,
"h": 1080
},
{
"x": 0,
"y": 0,
"w": 1080,
"h": 1080
}
]
},
"media_results": {
"result": {
"media_key": "3_1940878251477585920"
}
}
}
],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "1888058644434141184",
"name": "DeepEval",
"screen_name": "deepeval",
"indices": [
21,
30
]
}
]
},
"extended_entities": {
"media": [
{
"display_url": "pic.x.com/oiI52T58NW",
"expanded_url": "https://x.com/llama_index/status/1940878254954762369/photo/1",
"id_str": "1940878251477585920",
"indices": [
271,
294
],
"media_key": "3_1940878251477585920",
"media_url_https": "https://pbs.twimg.com/media/Gu9ifIuaUAAMQ9Y.jpg",
"type": "photo",
"url": "https://t.co/oiI52T58NW",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {
"faces": [
{
"x": 317,
"y": 504,
"h": 131,
"w": 131
},
{
"x": 133,
"y": 61,
"h": 264,
"w": 264
}
]
},
"medium": {
"faces": [
{
"x": 317,
"y": 504,
"h": 131,
"w": 131
},
{
"x": 133,
"y": 61,
"h": 264,
"w": 264
}
]
},
"small": {
"faces": [
{
"x": 199,
"y": 317,
"h": 82,
"w": 82
},
{
"x": 83,
"y": 38,
"h": 166,
"w": 166
}
]
},
"orig": {
"faces": [
{
"x": 317,
"y": 504,
"h": 131,
"w": 131
},
{
"x": 133,
"y": 61,
"h": 264,
"w": 264
}
]
}
},
"sizes": {
"large": {
"h": 1080,
"w": 1080,
"resize": "fit"
},
"medium": {
"h": 1080,
"w": 1080,
"resize": "fit"
},
"small": {
"h": 680,
"w": 680,
"resize": "fit"
},
"thumb": {
"h": 150,
"w": 150,
"resize": "crop"
}
},
"original_info": {
"height": 1080,
"width": 1080,
"focus_rects": [
{
"x": 0,
"y": 0,
"w": 1080,
"h": 605
},
{
"x": 0,
"y": 0,
"w": 1080,
"h": 1080
},
{
"x": 67,
"y": 0,
"w": 947,
"h": 1080
},
{
"x": 270,
"y": 0,
"w": 540,
"h": 1080
},
{
"x": 0,
"y": 0,
"w": 1080,
"h": 1080
}
]
},
"media_results": {
"result": {
"media_key": "3_1940878251477585920"
}
}
}
]
},
"favorite_count": 27,
"favorited": false,
"full_text": "This guest post from @deepeval shows you how to build better RAG applications by combining LlamaIndex with comprehensive evaluation:\n\n🎯 Use Answer Relevancy, Faithfulness, and Contextual Precision metrics to measure both your retriever and generator components\n🔧 Set up… https://t.co/oiI52T58NW",
"is_quote_status": false,
"lang": "en",
"possibly_sensitive": false,
"possibly_sensitive_editable": true,
"quote_count": 0,
"reply_count": 0,
"retweet_count": 5,
"retweeted": false,
"user_id_str": "1604278358296055808",
"id_str": "1940878254954762369"
},
"quick_promote_eligibility": {
"eligibility": "IneligibleNotProfessional"
}
}
},
"tweetDisplayType": "Tweet"
},
"clientEventInfo": {
"component": "tweet",
"element": "tweet"
}
}
},
{
"entryId": "cursor-bottom-1953485864407400447",
"sortIndex": "1953485864407400447",
"content": {
"entryType": "TimelineTimelineCursor",
"__typename": "TimelineTimelineCursor",
"value": "DAAFCgABGxwtCy2___0LAAIAAAAoRW1QQzZ3QUFBZlEvZ0dKTjB2R3AvQUFBQUFFYTcySjlXdHZRZ1E9PQgAAwAAAAIAAA",
"cursorType": "Bottom"
}
}
]
},
{
"type": "TimelineTerminateTimeline",
"direction": "Top"
},
{
"type": "TimelineTerminateTimeline",
"direction": "Bottom"
}
],
"metadata": {
"scribeConfig": {
"page": "ranked_replies"
}
}
}
}
}