add invocation params as extra params in llm callbacks (langchain-ai#…

…4506)

# Your PR Title (What it does)

<!--
Thank you for contributing to LangChain! Your PR will appear in our next
release under the title you set. Please make sure it highlights your
valuable contribution.

Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.

After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.
-->

<!-- Remove if not applicable -->

Fixes # (issue)

## Before submitting

<!-- If you're adding a new integration, include an integration test and
an example notebook showing its use! -->

## Who can review?

Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:

<!-- For a quicker response, figure out the right person to tag with @

        @hwchase17 - project lead

        Tracing / Callbacks
        - @agola11

        Async
        - @agola11

        DataLoader Abstractions
        - @eyurtsev

        LLM/Chat Wrappers
        - @hwchase17
        - @agola11

        Tools / Toolkits
        - @vowelparrot
 -->

langchain/llms/base.py

@@ -149,6 +149,14 @@ def generate(
                 "Argument 'prompts' is expected to be of type List[str], received"
                 f" argument of type {type(prompts)}."
             )
+        params = self.dict()
+        params["stop"] = stop
+        (
+            existing_prompts,
+            llm_string,
+            missing_prompt_idxs,
+            missing_prompts,
+        ) = get_prompts(params, prompts)
         disregard_cache = self.cache is not None and not self.cache
         callback_manager = CallbackManager.configure(
             callbacks, self.callbacks, self.verbose
@@ -163,7 +171,7 @@ def generate(
                     "Asked to cache, but no cache found at `langchain.cache`."
                 )
             run_manager = callback_manager.on_llm_start(
-                {"name": self.__class__.__name__}, prompts
+                {"name": self.__class__.__name__}, prompts, invocation_params=params
             )
             try:
                 output = (
@@ -176,17 +184,11 @@ def generate(
                 raise e
             run_manager.on_llm_end(output)
             return output
-        params = self.dict()
-        params["stop"] = stop
-        (
-            existing_prompts,
-            llm_string,
-            missing_prompt_idxs,
-            missing_prompts,
-        ) = get_prompts(params, prompts)
         if len(missing_prompts) > 0:
             run_manager = callback_manager.on_llm_start(
-                {"name": self.__class__.__name__}, missing_prompts
+                {"name": self.__class__.__name__},
+                missing_prompts,
+                invocation_params=params,
             )
             try:
                 new_results = (
@@ -213,6 +215,14 @@ async def agenerate(
         callbacks: Callbacks = None,
     ) -> LLMResult:
         """Run the LLM on the given prompt and input."""
+        params = self.dict()
+        params["stop"] = stop
+        (
+            existing_prompts,
+            llm_string,
+            missing_prompt_idxs,
+            missing_prompts,
+        ) = get_prompts(params, prompts)
         disregard_cache = self.cache is not None and not self.cache
         callback_manager = AsyncCallbackManager.configure(
             callbacks, self.callbacks, self.verbose
@@ -227,7 +237,7 @@ async def agenerate(
                     "Asked to cache, but no cache found at `langchain.cache`."
                 )
             run_manager = await callback_manager.on_llm_start(
-                {"name": self.__class__.__name__}, prompts
+                {"name": self.__class__.__name__}, prompts, invocation_params=params
             )
             try:
                 output = (
@@ -240,18 +250,11 @@ async def agenerate(
                 raise e
             await run_manager.on_llm_end(output, verbose=self.verbose)
             return output
-        params = self.dict()
-        params["stop"] = stop
-        (
-            existing_prompts,
-            llm_string,
-            missing_prompt_idxs,
-            missing_prompts,
-        ) = get_prompts(params, prompts)
         if len(missing_prompts) > 0:
             run_manager = await callback_manager.on_llm_start(
                 {"name": self.__class__.__name__},
                 missing_prompts,
+                invocation_params=params,
             )
             try:
                 new_results = (