# Using Assistant API Retrieval Hallucinates **URL:** \ **Category:** API\ **Tags:** gpt-4, hallucinations, prompt, assistants, assistants-api\ **Created:** [November 10, 2023, 6:10am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857 "2023-11-10T06:10:53Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![diego.cardenas](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/diego.cardenas/32/243048_2.png) [@diego.cardenas](https://community.openai.com/u/diego.cardenas)\ **Post date:** [November 10, 2023, 6:10am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/1 "2023-11-10T06:10:53Z")
Hello! I’m using the Assistant API. Created one with a JSON file that contains 50 products with description and important parameters. I also have a function that shows the title and ID of the product that is being recommended to the user. I’m having issues answering simple questions like: 1. Show me all the products that are from X category. 2. Show me all the products that have Y characteristic. Has anyone found the best file type and/or best file format that increases the performance of the assistants? As added context, I’ve tried the newer GTP4 turbo model and activating Code Interpreter. ---
**Author:** ![sergio.soto](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/sergio.soto/32/246755_2.png) [@sergio.soto](https://community.openai.com/u/sergio.soto)\ **Post date:** [November 13, 2023, 11:00am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/2 "2023-11-13T11:00:46Z")
I am having also hallucinations passing the info into a markdown file to a GPT4 turbo configured assistant. In my case the main issue is handing urls provided in he files. ---
**Author:** ![adrien.dulong](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/adrien.dulong/32/146345_2.png) [@adrien.dulong](https://community.openai.com/u/adrien.dulong)\ **Post date:** [November 13, 2023, 9:39pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/3 "2023-11-13T21:39:40Z")
I have the same issue. I uploaded JSON documents with various sport statistics and then even with simple question the assistant is not able to get them in the files. Event when I give it the exact file to search in he is not able I also tried to detail the role of every file in the description of the assistant but it does not work. I hope it’s just some issue indexing the files since it’s only the beginning. But for now it’s really not helpful. ---
**Author:** ![diego.cardenas](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/diego.cardenas/32/243048_2.png) [@diego.cardenas](https://community.openai.com/u/diego.cardenas)\ **Post date:** [November 13, 2023, 9:56pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/4 "2023-11-13T21:56:36Z")
Hey @sergio.soto and @adrien.dulong . I finally had success with the reliable and simple plain .TXT file. Not sure what your use case is but I’m managing a product catalog with almost 100 rows and every row with over 2000 characters. Final result, no hallucinations and was able to integrate well with functions. What has worked for my use case and tests is to create a CSV and pass that to a TXT file but using none common delimiters. For example, symbols instead of the typical commas and spaces. Hope this helps! ---
**Author:** ![sergio.soto](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/sergio.soto/32/246755_2.png) [@sergio.soto](https://community.openai.com/u/sergio.soto)\ **Post date:** [November 14, 2023, 8:53am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/5 "2023-11-14T08:53:37Z")
Hi @diego.cardenas , thank you for your comment! > [@diego.cardenas](#): > > Final result, no hallucinations and was able to integrate well with functions. What has worked for my use case and tests is to create a CSV and pass that to a TXT file but using none common delimiters. For example, symbols instead of the typical commas and spaces. This is essentially a markdown: first row has field titles and next rows are data separated by a `|` (vertical bar symbol). In my case the hallucinates are related with a field that is an url. Sometimes GPT4 removes the last number of the ID (is the end of the url), sometimes literally invent it. ---
**Author:** ![diego.cardenas](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/diego.cardenas/32/243048_2.png) [@diego.cardenas](https://community.openai.com/u/diego.cardenas)\ **Post date:** [November 14, 2023, 12:11pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/6 "2023-11-14T12:11:07Z")
Try encapsulating each content of the row and column in a . Again, the “|” or the commas and spaces isn’t enough. You could try converting the markdown or plain text file you have into CSV with GPT to see how it reads it. If you’re end results is a CSV with content out of place, you need to change the delimiters. ---
**Author:** ![zorluhan](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/zorluhan/32/451728_2.png) [@zorluhan](https://community.openai.com/u/zorluhan)\ **Post date:** [November 22, 2023, 10:15pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/7 "2023-11-22T22:15:21Z")
this created enormous improvement for us in terms of error rates. We are working with a 6000 product feed. Thank you Diego! ---
**Author:** ![PaulBellow](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/paulbellow/32/597962_2.png) [@PaulBellow](https://community.openai.com/u/PaulBellow)\ **Post date:** [November 22, 2023, 10:17pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/8 "2023-11-22T22:17:17Z")
Thanks for coming back to let us know. We love to hear this as a community! ---
**Author:** ![yurifromuk](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/yurifromuk/32/249570_2.png) [@yurifromuk](https://community.openai.com/u/yurifromuk)\ **Post date:** [November 27, 2023, 9:46am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/9 "2023-11-27T09:46:14Z")
@diego.cardenas Hey, Diego. I used symbols like ‘®’ as delimiters, but seems like the assistant can use only up to 10% of the file at once. The file itself is CSV with custom delimiters in a .txt file. It has about 2000 rows and each row has about 10 different values. Can you also throw some light on your experience with functions? Which functions helped your assistant to parse files efficiently? ---
**Author:** ![evandrofsouza.ad](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/evandrofsouza.ad/32/261487_2.png) [@evandrofsouza.ad](https://community.openai.com/u/evandrofsouza.ad)\ **Post date:** [November 27, 2023, 7:33pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/10 "2023-11-27T19:33:08Z")
Guys, is it possible to reach an specific file or assistant via API? I cound not find this example in documentation only to a specific API Key or via Playground. The problem you mentioned above I solved using double “” before and after and in the instruction reinforcing to mention the attached doc information ---
**Author:** ![yurifromuk](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/yurifromuk/32/249570_2.png) [@yurifromuk](https://community.openai.com/u/yurifromuk)\ **Post date:** [November 27, 2023, 10:38pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/11 "2023-11-27T22:38:10Z")
Use files api to upload file, create assistant and thread and attach file to it using new openai assistant api ---
**Author:** ![evandrofsouza.ad](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/evandrofsouza.ad/32/261487_2.png) [@evandrofsouza.ad](https://community.openai.com/u/evandrofsouza.ad)\ **Post date:** [November 28, 2023, 7:47pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/12 "2023-11-28T19:47:17Z")
So first I create an assistent \> get the assistant\_id \> then send the file \> and only after all I can run questions right? But How can ask to this new specific assistant\_id later for instance? ---
**Author:** ![evandrofsouza.ad](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/evandrofsouza.ad/32/261487_2.png) [@evandrofsouza.ad](https://community.openai.com/u/evandrofsouza.ad)\ **Post date:** [November 28, 2023, 10:44pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/13 "2023-11-28T22:44:47Z")
Just saw here in documentation everything worked fine (Upload file, created assistent and attached the file but right after I created a thread I got an error or this response : { “id”: “thread\_NyBgr6cYHo8iUGblB5OD16jA”, “object”: “thread”, “created\_at”: 1701210208, “metadata”: {} } I tried this [https://api.openai.com/v1/threads](https://api.openai.com/v1/threads) and this [https://api.openai.com/v1/threads/thread\_GQjV02uQ7eLwmwg1abBQGTX0/messages](https://api.openai.com/v1/threads/thread_GQjV02uQ7eLwmwg1abBQGTX0/messages) Right after I got the thread ID which post URL I should use in order to make the prompt to the specific file\_id? Thanks a thounsand for your assistance @yurifromuk ---
**Author:** ![brandondooley](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/brandondooley/32/235238_2.png) [@brandondooley](https://community.openai.com/u/brandondooley)\ **Post date:** [December 13, 2023, 1:23pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/14 "2023-12-13T13:23:56Z")
@diego.cardenas Would you be able to share a sample of the .txt file that you are using? Encountering similar problems here ---
**Author:** ![diego.cardenas](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/diego.cardenas/32/243048_2.png) [@diego.cardenas](https://community.openai.com/u/diego.cardenas)\ **Post date:** [December 14, 2023, 5:15am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/15 "2023-12-14T05:15:03Z")
Hey @yurifromuk ! Were you able to solve the issue you’re encountering? ---
**Author:** ![diego.cardenas](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/diego.cardenas/32/243048_2.png) [@diego.cardenas](https://community.openai.com/u/diego.cardenas)\ **Post date:** [December 14, 2023, 5:20am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/16 "2023-12-14T05:20:50Z")
Sure thing! I have noticed a decrease in efficiency for an assistant that was working perfectly and now is not. Not sure if it’s some changes going on to the Assistants since it’s still in beta. Anyways, here is the document. I’m sending over an example. Please share what results you’re getting. The file type is TXT (plain text file) and the content is the following: ```auto |product_retailer_id|title|description|availability|condition|price|sale_price|category|brand| |---|---|---|---|---|---|---|---|---| |['10001']|['CB250 TWISTER GRIS']|['Agresiva de corazón, ágil de diseño. La nueva CB250 Twister, es una motocicleta hecha para derrotar a todo lo que, se cruce en su camino.



Características:
• Marcas: Honda
• Tipos de moto: Pisteras
• Color: Gris
• Cilindrada: 249.6 cc
• Tipo de motor: Refrigerado por aire\, 4 tiempos\, OHC
• Potencia: 22.1 HP / 7500 rpm
• Transmisión: 6 velocidades
• Freno Delantero: Disco
• Freno posterior: Disco
• Suspensión Delantera: Telescópica
• Suspensión Posterior: Monoamortiguado
• Meses de garantia: 12
• Cantidad de ruedas: Lineal
• Tipo de transmisión: 6 velocidades
• Tipo de Frenos: Disco']|['in stock']|['new']|['PEN 20099.00']||['Pisteras']|['Honda']| |['10002']|['EVO 125 ROJO']|['Rápida, livina y económica. Precisa para aquellos que por primera vez manejarán una moto, siendo ligera e ideal para el desplazamiento diario
Si lo que buscas es comodidad a la hora de manejar en la ciudad, las motos con transmisión automática son ideales y cuentan con espacios para llevar algo de equipaje en su interior y están pensadas para la altura de todo tipo de conductores.



Características:
• Marcas: Zongshen
• Tipos de moto: Scooter
• Color: Rojo
• Cilindrada: 125.0 cc
• Tipo de motor: 4 tiempos SOHC
• Potencia: 9.10 HP a 8\,000 rpm
• Transmisión: Automática
• Freno Delantero: Disco
• Freno posterior: Tambor
• Suspensión Delantera: Horquillas telescópicas
• Suspensión Posterior: Mono amortiguador
• Meses de garantia: 12
• Kilometros de garantia: 10\,000
• Cantidad de ruedas: Lineal
• Tipo de Frenos: Disco, Tambor
• Tipo de transmisión: Automática']|['in stock']|['new']|['PEN 4419.00']||['Scooter']|['Zongshen']| ``` ---
**Author:** ![brandondooley](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/brandondooley/32/235238_2.png) [@brandondooley](https://community.openai.com/u/brandondooley)\ **Post date:** [December 14, 2023, 8:26am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/17 "2023-12-14T08:26:28Z")
Thanks @diego.cardenas ! This is an interesting approach, shall give it a shot on my end. ---
**Author:** ![nate.york](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/nate.york/32/283185_2.png) [@nate.york](https://community.openai.com/u/nate.york)\ **Post date:** [January 5, 2024, 11:31pm UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/18 "2024-01-05T23:31:12Z")
This worked for me, thank you @diego.cardenas and team! Exported a Flat 2D Table from Excel into a Tab Delimited and using Code Interpreter I am getting the results I am looking for, matching incoming descriptions to nodes in my data based on the terms I have for them. It is doing some pretty advanced reasoning right out of the gate, although it is very, very slow. No worries, now that I have a basic version working I can start to break and iterate 😄 This was a lot of trial and error, I see so many people out here trying to do something similar, looking up values tabular data, hopefully devs address this need. ---
**Author:** ![stevenic](https://avatars.discourse-cdn.com/v4/letter/s/e480ec/32.png) [@stevenic](https://community.openai.com/u/stevenic)\ **Post date:** [January 6, 2024, 12:17am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/19 "2024-01-06T00:17:00Z")
A couple of tips without specifically knowing how OpenAI is splitting documents… I’m going to just assume that they’re using Lang Chains Recursive Text Splitter class or some variant. For markdown specifically, you want to use headers to separate out chunks of related information. Using #, ##, and ### you can actually control the chunking of data into their Vector DB and therefor steer the model. I don’t know what their chunk size is but its probably somewhere around 400 tokens (if not exactly 400 tokens) so try to keep chunks of related data around this size. Models don’t have any sort of spatial awareness with regards to table data so showing them data using markdown tables is likely to have mixed results. You should reformat any tables to be a list of records. I’ll give an example: ```md | Name | Age | Title | | ------- | ---- | -------- | | Steve | 55 | Founder | | Paul | 48 | Founder | | Brian | 35 | Engineer | ``` Should be presented to the model as: ```md ### Steve Age: 55 Title: Founder ### Paul Age: 48 Title: Founder ### Brian Age: 35 Title: Engineer ``` You really want to present table data to the model as whole record chunks where possible. My final tip is to think about how the users query matches semantically to the chunks your searching over… Every chunk needs to map to a concept for cosine similarity to work. If you have a chunk of text that’s “| 5’10 | 55 | 4 |” what concepts does that chunk of text map to? If your chunk is instead “height: 5’10, age: 55, dependents: 4”, there are 3 clear concepts that this chunk maps to. So a query for “show me people over 50 with 3 or more dependents” has a much better chance of retrieving the second chunk then the first one. Keep in mind though that these models are horribly at both math and counting so it’s a crap shoot if that query works in the first place. But without encoding the concepts into the chunk you have zero shot of it working. Hope those tips help… ---
**Author:** ![stevenic](https://avatars.discourse-cdn.com/v4/letter/s/e480ec/32.png) [@stevenic](https://community.openai.com/u/stevenic)\ **Post date:** [January 6, 2024, 12:29am UTC](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857/20 "2024-01-06T00:29:29Z")
Here’s an example document from a test corpus I’m working with called Bowl Season. Bowl Season contains 42 documents currently (43 after next Monday) which summarize the details and outcome of all 43 college football bowl games. So each game is a separate document in the corpus: ```md # Capital One Orange Bowl Georgia Bulldogs (13-1) Q1: 7 Q2: 35 Q3: 14 Q4: 7 TOTAL: 63 Florida State Seminoles (13-1) Q1: 0 Q2: 3 Q3: 0 Q4: 0 TOTAL: 3 ## Game Information Hard Rock Stadium Miami Gardens, FL 4:00 PM EST, December 30, 2023 Coverage: ESPN/ESPN+ Line: UGA -23.5 Over/Under: 47.5 Attendance: 63,324 (97%) CAPACITY: 64,992 ## Game Leaders ### Passing Yards UGA C. Beck 13-18, 203 YDS, 2 TD FSU B. Glenn 9-26, 139 YDS, 2 INT ### Rushing Yards UGA K. Milton 9 CAR, 104 YDS, 2 TD FSU J. Douglas 8 CAR, 46 YDS ### Receiving Yards UGA D. Bell 5 REC, 86 YDS FSU K. Poitier 4 REC, 84 YDS ## Team Stats ### Total Yards UGA: 673 FSU: 209 ### Turnovers UGA: 0 FSU: 4 ### 1st Downs UGA: 36 FSU: 11 ### Possession UGA: 35:38 FSU: 24:22 ## Scoring Summary ### 1ST QUARTER Georgia Bulldogs TD 4:05 Kendall Milton 15 Yd Run (Peyton Woodring Kick) 7 plays, 69 yards, 2:40 ### 2ND QUARTER Georgia Bulldogs TD 14:57 Kendall Milton 5 Yd Run (Peyton Woodring Kick) 6 plays, 82 yards, 1:56 Florida State Seminoles FG 12:34 Ryan Fitzgerald 22 Yd Field Goal 6 plays, 71 yards, 2:23 Georgia Bulldogs TD 10:38 Daijun Edwards 15 Yd Run (Peyton Woodring Kick) 4 plays, 75 yards, 1:56 Georgia Bulldogs TD 10:18 Ladd McConkey 27 Yd Run (Peyton Woodring Kick) 1 play, 27 yards, 0:20 Georgia Bulldogs TD 3:39 Arian Smith 12 Yd pass from Carson Beck (Peyton Woodring Kick) 5 plays, 62 yards, 2:20 Georgia Bulldogs TD 0:24 Dominic Lovett 2 Yd pass from Carson Beck (Peyton Woodring Kick) 3 plays, 51 yards, 0:25 ### 3RD QUARTER Georgia Bulldogs TD 9:23 Daijun Edwards 2 Yd Run (Peyton Woodring Kick) 10 plays, 75 yards, 5:37 Georgia Bulldogs TD 2:30 Lawson Luckie 4 Yd pass from Gunner Stockton (Peyton Woodring Kick) 10 plays, 90 yards, 4:31 ### 4TH QUARTER Georgia Bulldogs TD 12:10 Anthony Evans III 14 Yd pass from Gunner Stockton (Peyton Woodring Kick) 9 plays, 84 yards, 4:31 ``` You can see how I’m using headers to control the chunking of the data. The system I’m building to consume this corpus is already capable of accurately answering questions like “tell me the final score of every bowl game and the player from each game that had the most receiving yards” Both GPT-4 and GPT-3.5 can accurately return both for all 42 games. There are more tricks needed to make that work then just proper data prep, but data prep is super important. One more tip is that ideally you want to present the model with a condensed version of the document that contains all the information needed to answer the question while retaining the general structure of the source document. So lets the say the query is “what games played in Florida had 4th quarter scores by the winner?” This is the ideal text you would show the model: ```md # Capital One Orange Bowl Georgia Bulldogs (13-1) Q1: 7 Q2: 35 Q3: 14 Q4: 7 TOTAL: 63 Florida State Seminoles (13-1) Q1: 0 Q2: 3 Q3: 0 Q4: 0 TOTAL: 3 ## Game Information Hard Rock Stadium Miami Gardens, FL 4:00 PM EST, December 30, 2023 ## Scoring Summary ### 4TH QUARTER Georgia Bulldogs TD 12:10 Anthony Evans III 14 Yd pass from Gunner Stockton (Peyton Woodring Kick) 9 plays, 84 yards, 4:31 ``` That is the minimum information needed for the model to answer that question. The challenge is working out that’s the text you need to show the model. And here’s GPT 3.5’s answer to that question: ![image](https://us1.discourse-cdn.com/openai1/original/4X/b/1/9/b19e60d8186364457f96ddb0a765318278baa21e.png) [Next page](https://community.openai.com/t/using-assistant-api-retrieval-hallucinates/491857.md?page=2)