Formed in 2009, the Archive Team (not to be confused with the archive.org Archive-It Team) is a rogue archivist collective dedicated to saving copies of rapidly dying or deleted websites for the sake of history and digital heritage. The group is 100% composed of volunteers and interested parties, and has expanded into a large amount of related projects for saving online and digital history.
History is littered with hundreds of conflicts over the future of a community, group, location or business that were "resolved" when one of the parties stepped ahead and destroyed what was there. With the original point of contention destroyed, the debates would fall to the wayside. Archive Team believes that by duplicated condemned data, the conversation and debate can continue, as well as the richness and insight gained by keeping the materials. Our projects have ranged in size from a single volunteer downloading the data to a small-but-critical site, to over 100 volunteers stepping forward to acquire terabytes of user-created data to save for future generations.
The main site for Archive Team is at archiveteam.org and contains up to the date information on various projects, manifestos, plans and walkthroughs.
This collection contains the output of many Archive Team projects, both ongoing and completed. Thanks to the generous providing of disk space by the Internet Archive, multi-terabyte datasets can be made available, as well as in use by the Wayback Machine, providing a path back to lost websites and work.
Our collection has grown to the point of having sub-collections for the type of data we acquire. If you are seeking to browse the contents of these collections, the Wayback Machine is the best first stop. Otherwise, you are free to dig into the stacks to see what you may find.
The Archive Team Panic Downloads are full pulldowns of currently extant websites, meant to serve as emergency backups for needed sites that are in danger of closing, or which will be missed dearly if suddenly lost due to hard drive crashes or server failures.
ArchiveBot is an IRC bot designed to automate the archival of smaller websites (e.g. up to a few hundred thousand URLs). You give it a URL to start at, and it grabs all content under that URL, records it in a WARC, and then uploads that WARC to ArchiveTeam servers for eventual injection into the Internet Archive (or other archive sites).
To use ArchiveBot, drop by #archivebot on EFNet. To interact with ArchiveBot, you issue commands by typing it into the channel. Note you will need channel operator permissions in order to issue archiving jobs. The dashboard shows the sites being downloaded currently.
The Wayback Machine - https://web.archive.org/web/20260411152714/https://community.openai.com/t/vector-storage-rag-ai-agent-not-retrieving-data-beyond-midpoint-of-uploaded-csv/1378766
I’m encountering an issue reported by a customer and was able to reproduce it myself.
The scenario is as follows:
A CSV file (~1MB) with ~500 rows and 2 simple columns (SKU, Inventory) is uploaded.
When querying the AI agent to check stock for specific SKUs, it successfully retrieves results from the beginning of the file.
However, from approximately the middle of the dataset onwards, the AI consistently fails to return results.
To validate this further, I tested with a different dataset (a list of shops in Mall of the Emirates). I queried the AI sequentially:
The first ~1–1.5 pages of entries are retrieved correctly.
After that point, the AI stops returning results for the remaining entries.
This behavior appears very consistent and predictable, which makes me suspect a limitation or misconfiguration rather than random failure.
Has anyone encountered something similar or can provide insight into what might be causing this? At the moment, this significantly limits the usefulness of the feature.
Your post does not describe which API or product or software that you are using. Indeed, you could even be discussing a non-OpenAI solution when you only provide us “querying the AI agent” and “vector storage RAG”.
The chief concern is that CSV is not a supported file type for OpenAI vector stores. File search | OpenAI API
The reason for the failing on CSV as a data format for vector stores is that if it were supplied as a plain text file so it could be ingested, a CSV typically has a header row with the column labels. The document extraction then splits this text into chunks, and the splits of the file after the first chunk have no header of the data fields describing the purpose.
Embeddings-based semantic search works best where the document, when split, has natural language information about a topic and subject in every chunk, that can stand alone as knowledge, to then return a score for how similar the query is to each chunk being individually evaluated.
A SKU + quantity has no information with useful semantic correlation: 58826682, 3 85388662, 10
There are not learned embedding layers that can match token 588 to a query how many 5838666 do we have on hand?, as there is little distinguishing of meaning. Then, the embeddings has been provided many rows of data in a chunk, essentially making any search (beyond the first chunk with a legend with the word “SKU”) meaningless.
If you need database-like search, you will likely need to use a different technique, or even prepare the database for query by field. This is not a solved AI problem for arbitrary user-provided data - except for providing everything as input to a large-context AI model.
We are using realtime api (1.5 and mini), and gpt 5.4 for chat completions. + OpenAI Python SDK’s Vector Stores API.
And the embedding model of openai. (Which as I see we have no control of) but for sure it is one of the best out there because that’s what our research showed.
CSV not supported okay. So I tried with PDF which is supported.
It also happens with a PDF
Lets put aside the SKU example because I agree - thats the work of a Database tool. Lets make it simpler.
Example: I have a pdf with a list of participating brands at the mall of the Emirates. This is page 1.
Formed in 2009, the Archive Team (not to be confused with the archive.org Archive-It Team) is a rogue archivist collective dedicated to saving copies of rapidly dying or deleted websites for the sake of history and digital heritage. The group is 100% composed of volunteers and interested parties, and has expanded into a large amount of related projects for saving online and digital history.
