Title: feat/
Open Graph Title: feat/
X Title: feat/
Description: Is your feature request related to a problem? Please describe. . Ex. I'm always frustrated when Yes. I'm currently using the Unstructured API with chunking_strategy="by_title" to segment documents for downstream semantic search and RAG a...
Open Graph Description: Is your feature request related to a problem? Please describe. . Ex. I'm always frustrated when Yes. I'm currently using the Unstructured API with chunking_strategy="by_title" to segment documents ...
X Description: Is your feature request related to a problem? Please describe. . Ex. I'm always frustrated when Yes. I'm currently using the Unstructured API with chunking_strategy="by_title" to ...
Opengraph URL: https://github.com/Unstructured-IO/unstructured-python-client/issues/258
X: @github
Domain: github.com
{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"feat/\u003cshort-name\u003e either add parameter \"extract_image_block_output_dir\" in unstructured api call of shared.PartitionParameters or include base46 encoded images in meta data when chunking stratergy =\"by_title\"","articleBody":"**Is your feature request related to a problem? Please describe.**\n. Ex. I'm always frustrated when Yes. I'm currently using the Unstructured API with chunking_strategy=\"by_title\" to segment documents for downstream semantic search and RAG applications. However, when using this chunking strategy, I’m unable to retrieve the Base64-encoded images in the document (i.e., no image_base64 in the metadata of returned elements). Additionally, the parameter \"extract_image_block_output_dir\"—which allows extracted image blocks to be saved—is unavailable or not functioning when is used. unstructured by api call\n\nThis prevents me from building a robust multimodal pipeline that includes both structured text chunks and their corresponding visual content.\n\n**Describe the solution you'd like**\nI’d like one of the following to be supported when using chunking_strategy=\"by_title\" in the Unstructured API:\n\n(Preferred) Embed Base64-encoded image (image_base64) in the metadata of returned elements—just as is supported in r hi-res strategies.\n\n(Alternative) Enable the extract_image_block_output_dir parameter to work unstructured by api call , so that extracted image blocks are saved to a specified directory even during chunked extraction.\n\n**Describe alternatives you've considered**\nA clear and concise description of any alternative solutions or features you've considered.\n\n**Additional context**\nAdd any other context or screenshots about the feature request here.\n","author":{"url":"https://github.com/mahendra867","@type":"Person","name":"mahendra867"},"datePublished":"2025-04-05T21:36:02.000Z","interactionStatistic":{"@type":"InteractionCounter","interactionType":"https://schema.org/CommentAction","userInteractionCount":0},"url":"https://github.com/258/unstructured-python-client/issues/258"}
| route-pattern | /_view_fragments/issues/show/:user_id/:repository/:id/issue_layout(.:format) |
| route-controller | voltron_issues_fragments |
| route-action | issue_layout |
| fetch-nonce | v2:8208a120-ea07-a4e4-d828-66db5d53efaf |
| current-catalog-service-hash | 81bb79d38c15960b92d99bca9288a9108c7a47b18f2423d0f6438c5b7bcd2114 |
| request-id | C430:348185:4894598:6181E5E:6964E21D |
| html-safe-nonce | cf82a489e188ee79a75c1917ea5aeaf7a54a4c85bf21d3e5d3ca0ad34cef043a |
| visitor-payload | eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJDNDMwOjM0ODE4NTo0ODk0NTk4OjYxODFFNUU6Njk2NEUyMUQiLCJ2aXNpdG9yX2lkIjoiNzkyMjU3NTQ3NTczNDc5ODg3NyIsInJlZ2lvbl9lZGdlIjoiaWFkIiwicmVnaW9uX3JlbmRlciI6ImlhZCJ9 |
| visitor-hmac | 9704b4596a3bf3438aa456737b05dc27851c31dcaccfcb9466112bebdbf03af5 |
| hovercard-subject-tag | issue:2974516741 |
| github-keyboard-shortcuts | repository,issues,copilot |
| google-site-verification | Apib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I |
| octolytics-url | https://collector.github.com/github/collect |
| analytics-location | / |
| fb:app_id | 1401488693436528 |
| apple-itunes-app | app-id=1477376905, app-argument=https://github.com/_view_fragments/issues/show/Unstructured-IO/unstructured-python-client/258/issue_layout |
| twitter:image | https://opengraph.githubassets.com/4f85106c3dc318f5fcc6aa1e8d9d59cc8808cd4b6f48526c2d36ae00e7f3ca06/Unstructured-IO/unstructured-python-client/issues/258 |
| twitter:card | summary_large_image |
| og:image | https://opengraph.githubassets.com/4f85106c3dc318f5fcc6aa1e8d9d59cc8808cd4b6f48526c2d36ae00e7f3ca06/Unstructured-IO/unstructured-python-client/issues/258 |
| og:image:alt | Is your feature request related to a problem? Please describe. . Ex. I'm always frustrated when Yes. I'm currently using the Unstructured API with chunking_strategy="by_title" to segment documents ... |
| og:image:width | 1200 |
| og:image:height | 600 |
| og:site_name | GitHub |
| og:type | object |
| og:author:username | mahendra867 |
| hostname | github.com |
| expected-hostname | github.com |
| None | 5838582163a1256e5ebd5086b7e1dc5cea93d82086c9c8b1395fb50f6ddab28d |
| turbo-cache-control | no-preview |
| go-import | github.com/Unstructured-IO/unstructured-python-client git https://github.com/Unstructured-IO/unstructured-python-client.git |
| octolytics-dimension-user_id | 108372208 |
| octolytics-dimension-user_login | Unstructured-IO |
| octolytics-dimension-repository_id | 689850105 |
| octolytics-dimension-repository_nwo | Unstructured-IO/unstructured-python-client |
| octolytics-dimension-repository_public | true |
| octolytics-dimension-repository_is_fork | false |
| octolytics-dimension-repository_network_root_id | 689850105 |
| octolytics-dimension-repository_network_root_nwo | Unstructured-IO/unstructured-python-client |
| turbo-body-classes | logged-out env-production page-responsive |
| disable-turbo | false |
| browser-stats-url | https://api.github.com/_private/browser/stats |
| browser-errors-url | https://api.github.com/_private/browser/errors |
| release | 8edad3509fd3b4374694551987974bbbcfd316c0 |
| ui-target | full |
| theme-color | #1e2327 |
| color-scheme | light dark |
Links:
Viewport: width=device-width