Nuno Campos and GitHub
52621bb803
Merge pull request #288 from langchain-ai/nc/8apr/cond-edge-multiple-destinations
...
feat: Return multiple destinations from conditional edge
2024-04-08 17:38:17 -07:00
Nuno Campos
fd6f44a7e4
feat: Return multiple destinations from conditional edge
2024-04-08 17:05:16 -07:00
ce687403d4
Fix single/double quotes in storm.ipynb ( #225 )
...
to avoid "unterminated string literal" error when run in Jupyter
Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com >
2024-04-08 13:42:53 -07:00
Ronen Azachi and GitHub
deabce5780
added packages to run multi-agent collaboration notebook ( #282 )
...
Added packages to be able to run the notebook
2024-04-08 13:41:58 -07:00
William FH and GitHub
2e9e3b0a6c
Initial MKDocs ( #285 )
2024-04-08 13:40:21 -07:00
Lance Martin and GitHub
a3c4d4bdd1
Merge pull request #273 from langchain-ai/rlm/claude3-code-gen
...
Clean code-gen ntbk
2024-04-07 17:21:15 -07:00
Lance Martin
fdc34ef3b7
Fmt
2024-04-07 16:00:18 -07:00
Lance Martin
04668df9bc
Add Claude3 evals
2024-04-07 15:55:37 -07:00
Lance Martin and GitHub
ca1c936d72
Merge pull request #284 from langchain-ai/rlm/adaptive_rag_local
...
Update local adaptive RAG ntbk
2024-04-06 17:30:06 -07:00
Lance Martin
5f8add89c3
Clean / test
2024-04-06 13:31:48 -07:00
Lance Martin
520443d6cd
Clean up code for Claude3
2024-04-06 13:20:39 -07:00
Misraaks and GitHub
217321127f
Issue #274 : Fix LLMCompiler Bugs ( #275 )
...
* Update LLMCompiler.ipynb
The code didn't actually handle when there's more than one dependency listed in an argument. The example of multi-step math used in the code doesn't work because the third step has more than one dependency in its args and the code only handles one:
```
User query: "What's ((3*(4+5)/0.5)+3245) + 8? What's 32/4.23? What's the sum of those two values?"
1. math(problem="((3*(4+5)/0.5)+3245) + 8")
2. math(problem="32/4.23")
3. math(problem="${1}+${2}")
4. join()<END_OFPLAN>
```
Step 3 fails, and does so silently too. It correctly parses strings that are "${1}", but not multi-argument strings like "${1}+${2}"
This fixes it to handle any number of dependencies listed in one arg. It uses the regex pattern already defined in output_parser.py.
* Fix looping function calls because no arg context
Task Fetching Unit, when it inserts the tool_messages, the function args don't get logged with function calls, this causes the replanner to loop and use the same function parameters and never corrects itself.
* Fix tool index count and range
In the planner prompt formatting, the 'num_tools' variable needs to have a +1 added to it because we're appending the join() function, without +1 it says there's one less available tools than there actually is because it only counts the passed in functions and not the join() function. And add +1 for listing otherwise it starts at a 0 offset.
* Fix unhandled empty iterator exception
Task fetching unit: When it calls the tools it doesn't handle when there's no tasks. next() is called and fails. This fixes it by wrapping in a try/except. On exception we set tasks to an empty list since next() failed, there's no tasks.
2024-04-05 10:37:11 -07:00
Nuno Campos and GitHub
70c1c996a4
Merge pull request #279 from langchain-ai/eugene/document_using_nuno_bot
...
Document Checkpoint
2024-04-04 15:02:48 -07:00
Nuno Campos
f21cc3f282
0.0.32
2024-04-04 13:22:08 -07:00
Eugene Yurtsev
21ce575739
x
2024-04-04 15:01:03 -04:00
Eugene Yurtsev
75ce4474e5
x
2024-04-04 14:57:52 -04:00
Lance Martin and GitHub
657bd7d8c3
Merge pull request #271 from langchain-ai/rlm/cohere
...
Cohere adaptive RAG
2024-04-03 21:44:06 -07:00
Lance Martin
c43de8637c
Finalize
2024-04-03 21:39:56 -07:00
Lance Martin
e779b4335b
Finalize ntbk w/ GPT-4
2024-04-03 21:27:50 -07:00
Nuno Campos and GitHub
322763436b
Merge pull request #276 from langchain-ai/nc/3apr/node-tracing-output
...
Ensure node tracing output is exactly what was returned from node
2024-04-03 17:39:04 -07:00
Lance Martin
fe87c43375
Update notebook
2024-04-03 15:10:25 -07:00
Nuno Campos
db3219f77c
Ensure node tracing output is exactly what was returned from node
2024-04-03 13:13:04 -07:00
Lance Martin
a984c65b6d
Clean ntbk
2024-04-03 11:34:25 -07:00
Lance Martin
1257518789
Cohere adaptive RAG
2024-04-02 21:56:10 -07:00
Nuno Campos and GitHub
e30d5f13bf
Merge pull request #270 from langchain-ai/nc/2apr/update-rag-notebook
...
Update adaptive rag notebook to use invoke
2024-04-02 17:25:11 -07:00
Nuno Campos
05009d8068
Update adaptive rag notebook to use invoke
2024-04-02 16:53:56 -07:00
Nuno Campos and GitHub
1961482e2b
Merge pull request #269 from langchain-ai/nc/2apr/add-langsmith-urls-time-travel
...
Add LangSmith run urls in time travel notebook
2024-04-02 16:14:17 -07:00
Nuno Campos
f269db4d58
Add LangSmith run urls in time travel notebook
2024-04-02 16:11:48 -07:00
Nuno Campos
d00d8913ca
0.0.31
2024-04-02 15:56:33 -07:00
Nuno Campos and GitHub
6fbb58c89f
Merge pull request #267 from langchain-ai/nc/2apr/optimize-tracing-output
...
Optimize tracing output of Graph/StateGraph/MessageGraph
2024-04-02 15:32:24 -07:00
Nuno Campos
617591ad42
Update time travel notebook
2024-04-02 14:51:14 -07:00
Nuno Campos
2f8ae4fdb4
Simplify tool executor
2024-04-02 14:46:14 -07:00
Nuno Campos
e3a9760bb2
Improve tracing output of state graph
2024-04-02 12:14:08 -07:00
Nuno Campos
2a299d070e
Optimize tracing output of Graph/StateGraph/MessageGraph
...
- control selection of relevant runs (needs langsmith release)
- see output of conditional edge function
- fix issue with conditional entry point not getting full state values as input
2024-04-02 10:32:47 -07:00
Nuno Campos and GitHub
041ca2f784
Merge pull request #263 from langchain-ai/nc/1apr/rename-channel-invoke
...
Rename ChannelInvoke to PregelNode
2024-04-01 19:37:12 -07:00
Nuno Campos
8b8171724c
Rename ChannelInvoke to PregelNode
...
- ChannelInvoke is a legacy name from when we had ChannelBatch
2024-04-01 19:34:13 -07:00
Nuno Campos and GitHub
8bdc66a867
Merge pull request #262 from langchain-ai/nc/1apr/message-graph-coerce
...
MessageGraph now accepts same shorthand message formats as langchain-core
2024-04-01 18:47:10 -07:00
Nuno Campos
a184600915
MessageGraph now accepts same shorthand message formats as langchain-core
2024-04-01 18:44:06 -07:00
Nuno Campos and GitHub
b1584a3980
Merge pull request #261 from langchain-ai/nc/1apr/test-state-custom-class
...
Add test and notebook for using pydantic base model as state object
2024-04-01 18:20:05 -07:00
Nuno Campos
694343c5b5
Update test
2024-04-01 18:03:52 -07:00
Nuno Campos
cbd2024dec
Add async test, add test for validation error
2024-04-01 17:56:18 -07:00
Nuno Campos and GitHub
2d042ed385
Merge pull request #260 from langchain-ai/nc/1apr/test-both-checkpoint-at
...
Add tests for both values of CheckpointAt
2024-04-01 17:51:38 -07:00
Nuno Campos
961ddd49ed
Add test and notebook for using pydantic base model as state object
2024-04-01 17:40:55 -07:00
Nuno Campos
f88ef74002
Add tests for both values of CheckpointAt
...
- fix bug when using at=END_OF_RUN together with interrupt_before
- fix bug when calling update_state after only node has run
- update some notebooks to new streaming format (ie. no __end__ node)
2024-04-01 17:17:39 -07:00
Nuno Campos and GitHub
1276547233
Merge pull request #258 from langchain-ai/nc/1apr/optimize-tracing-tree
...
Optimize tracing run tree
2024-04-01 16:16:54 -07:00
Nuno Campos and GitHub
dec8a53070
Merge pull request #257 from langchain-ai/nc/1apr/add-test-waiting-edge-via-branch
...
Add test for waiting edge triggered via conditional edge
2024-04-01 16:16:25 -07:00
Nuno Campos and GitHub
1632c045b1
Merge pull request #256 from langchain-ai/nc/1apr/docstrings-multi-edges
...
Add some more docstrings around multi edges
2024-04-01 16:16:17 -07:00
Nuno Campos and GitHub
a95d50c057
Merge pull request #254 from langchain-ai/nc/31mar/shorten-stack-traces
...
Remove some noisy frames from stack traces
2024-04-01 16:16:07 -07:00
Nuno Campos and GitHub
83b77824f0
Merge pull request #253 from langchain-ai/nc/31mar/rewrite-graph-compile
...
Rewrite Graph/StateGraph.compile()
2024-04-01 16:15:56 -07:00
Nuno Campos and GitHub
18112b4df8
Merge pull request #252 from langchain-ai/nc/31mar/channel-from-checkpoint-copy
...
Rename BaseChannel.empty() to BaseChannel.from_checkpoint()
2024-04-01 16:15:41 -07:00
