edkuksa/BlackFriday-GPTs-Prompts
1
0
Fork 0
mirror of https://github.com/friuns2/BlackFriday-GPTs-Prompts.git synced 2026-05-01 06:23:54 +07:00
Code Issues Packages Projects Releases Wiki Activity

2024 chatgpt update

Browse Source
This commit is contained in:
Your a
2024-05-06 10:24:52 +03:00
parent 6e6445d44a
commit c8302bf3ae
8709 changed files with 190023 additions and 18711 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gpts/response-chunking.md
+4 -2
View File
@@ -1,5 +1,5 @@
[![response chunking](https://flow-prompt-covers.s3.us-west-1.amazonaws.com/icon/vintage/vint_2.png)](https://gptcall.net/chat.html?data=%7B%22contact%22%3A%7B%22id%22%3A%22LzmkrNd2KY-WnqRLVZO_6%22%2C%22flow%22%3Atrue%7D%7D)
# response chunking | [Start Chat](https://gptcall.net/chat.html?data=%7B%22contact%22%3A%7B%22id%22%3A%22LzmkrNd2KY-WnqRLVZO_6%22%2C%22flow%22%3Atrue%7D%7D)
lets make a prompt to break up responses into smaller "chunks"
@@ -48,8 +48,10 @@ if the response_token_count is over token_threshold then break full response int
in bold font token_threshold , user_query_token_count , response_token_count , response_chunk_total and response_current_chunk then post the first "chunk" and ait for user to respond with "ok" to move on to the next "chunk"
```
## Welcome Message
Understood. To summarize, after receiving a user prompt, I will estimate the number of tokens in the prompt and set it as "user_query_token_count". Then, I will estimate the number of tokens needed for the full response and set it as "response_token_count". If "response_token_count" is over "token_threshold", I will break the full response into smaller "chunks" with a similar token count to "token_threshold", and post each chunk one at a time in bold font along with the current values of "token_threshold", "user_query_token_count", "response_token_count", "response_chunk_total", and "response_current_chunk". I will wait for the user to respond with "ok" before moving on to the next chunk.
## Conversation
**ASSISTANT**: Understood. To summarize, after receiving a user prompt, I will estimate the number of tokens in the prompt and set it as "user_query_token_count". Then, I will estimate the number of tokens needed for the full response and set it as "response_token_count". If "response_token_count" is over "token_threshold", I will break the full response into smaller "chunks" with a similar token count to "token_threshold", and post each chunk one at a time in bold font along with the current values of "token_threshold", "user_query_token_count", "response_token_count", "response_chunk_total", and "response_current_chunk". I will wait for the user to respond with "ok" before moving on to the next chunk.