kamp/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2024-09-21 03:40:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

Remove restrictions on pinned documents to use more context (#1248)

Browse Source 
* Remove restrictions on pinned documents to use more contet

* update comment
This commit is contained in:
Timothy Carambat 2024-05-01 13:32:52 -07:00 committed by GitHub
parent e61dfd80a5
commit 894f727903
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
server/utils/chats/embed.js
View File

@ -77,11 +77,10 @@ async function streamChatWithForEmbed(
chatMode
);
// Look for pinned documents and see if the user decided to use this feature. We will also do a vector search
// as pinning is a supplemental tool but it should be used with caution since it can easily blow up a context window.
// See stream.js comment for more information on this implementation.
await new DocumentManager({
workspace: embed.workspace,
maxTokens: LLMConnector.limits.system,
maxTokens: LLMConnector.promptWindowLimit(),
})
.pinnedDocs()
.then((pinnedDocs) => {

5
server/utils/chats/index.js
View File

@ -89,11 +89,10 @@ async function chatWithWorkspace(
chatMode,
});
// Look for pinned documents and see if the user decided to use this feature. We will also do a vector search
// as pinning is a supplemental tool but it should be used with caution since it can easily blow up a context window.
// See stream.js comment for more information on this implementation.
await new DocumentManager({
workspace,
maxTokens: LLMConnector.limits.system,
maxTokens: LLMConnector.promptWindowLimit(),
})
.pinnedDocs()
.then((pinnedDocs) => {

6
server/utils/chats/stream.js
View File

@ -105,9 +105,13 @@ async function streamChatWithWorkspace(
// Look for pinned documents and see if the user decided to use this feature. We will also do a vector search
// as pinning is a supplemental tool but it should be used with caution since it can easily blow up a context window.
// However we limit the maximum of appended context to 80% of its overall size, mostly because if it expands beyond this
// it will undergo prompt compression anyway to make it work. If there is so much pinned that the context here is bigger than
// what the model can support - it would get compressed anyway and that really is not the point of pinning. It is really best
// suited for high-context models.
await new DocumentManager({
workspace,
maxTokens: LLMConnector.limits.system,
maxTokens: LLMConnector.promptWindowLimit(),
})
.pinnedDocs()
.then((pinnedDocs) => {